Deep Reinforcement Learning via Policy Optimization
|
|
- Abel Caldwell
- 6 years ago
- Views:
Transcription
1 Deep Reinforcement Learning via Policy Optimization John Schulman July 3, 2017
2 Introduction
3 Deep Reinforcement Learning: What to Learn? Policies (select next action)
4 Deep Reinforcement Learning: What to Learn? Policies (select next action) Value functions (measure goodness of states or state-action pairs)
5 Deep Reinforcement Learning: What to Learn? Policies (select next action) Value functions (measure goodness of states or state-action pairs) Models (predict next states and rewards)
6 Model Free RL: (Rough) Taxonomy Policy Optimization Dynamic Programming modified policy iteration DFO / Evolution Policy Gradients Policy Iteration Value Iteration Actor-Critic Methods Q-Learning
7 Policy Optimization vs Dynamic Programming Conceptually...
8 Policy Optimization vs Dynamic Programming Conceptually... Policy optimization: optimize what you care about
9 Policy Optimization vs Dynamic Programming Conceptually... Policy optimization: optimize what you care about Dynamic programming: indirect, exploit the problem structure, self-consistency
10 Policy Optimization vs Dynamic Programming Conceptually... Policy optimization: optimize what you care about Dynamic programming: indirect, exploit the problem structure, self-consistency Empirically...
11 Policy Optimization vs Dynamic Programming Conceptually... Policy optimization: optimize what you care about Dynamic programming: indirect, exploit the problem structure, self-consistency Empirically... Policy optimization more versatile, dynamic programming methods more sample-efficient when they work
12 Policy Optimization vs Dynamic Programming Conceptually... Policy optimization: optimize what you care about Dynamic programming: indirect, exploit the problem structure, self-consistency Empirically... Policy optimization more versatile, dynamic programming methods more sample-efficient when they work Policy optimization methods more compatible with rich architectures (including recurrence) which add tasks other than control (auxiliary objectives), dynamic programming methods more compatible with exploration and off-policy learning
13 Parameterized Policies A family of policies indexed by parameter vector θ R d
14 Parameterized Policies A family of policies indexed by parameter vector θ R d Deterministic: a = π(s, θ)
15 Parameterized Policies A family of policies indexed by parameter vector θ R d Deterministic: a = π(s, θ) Stochastic: π(a s, θ)
16 Parameterized Policies A family of policies indexed by parameter vector θ R d Deterministic: a = π(s, θ) Stochastic: π(a s, θ) Analogous to classification or regression with input s, output a.
17 Parameterized Policies A family of policies indexed by parameter vector θ R d Deterministic: a = π(s, θ) Stochastic: π(a s, θ) Analogous to classification or regression with input s, output a. Discrete action space: network outputs vector of probabilities
18 Parameterized Policies A family of policies indexed by parameter vector θ R d Deterministic: a = π(s, θ) Stochastic: π(a s, θ) Analogous to classification or regression with input s, output a. Discrete action space: network outputs vector of probabilities Continuous action space: network outputs mean and diagonal covariance of Gaussian
19 Episodic Setting In each episode, the initial state is sampled from µ, and the agent acts until the terminal state is reached. For example:
20 Episodic Setting In each episode, the initial state is sampled from µ, and the agent acts until the terminal state is reached. For example: Taxi robot reaches its destination (termination = good)
21 Episodic Setting In each episode, the initial state is sampled from µ, and the agent acts until the terminal state is reached. For example: Taxi robot reaches its destination (termination = good) Waiter robot finishes a shift (fixed time)
22 Episodic Setting In each episode, the initial state is sampled from µ, and the agent acts until the terminal state is reached. For example: Taxi robot reaches its destination (termination = good) Waiter robot finishes a shift (fixed time) Walking robot falls over (termination = bad)
23 Episodic Setting In each episode, the initial state is sampled from µ, and the agent acts until the terminal state is reached. For example: Taxi robot reaches its destination (termination = good) Waiter robot finishes a shift (fixed time) Walking robot falls over (termination = bad) Goal: maximize expected return per episode maximize E [R π] π
24 Derivative Free Optimization / Evolution
25 Cross Entropy Method Initialize µ R d, σ R d for iteration = 1, 2,... do Collect n samples of θ i N(µ, diag(σ)) Perform one episode with each θ i, obtaining reward R i Select the top p% of θ samples (e.g. p = 20), the elite set Fit a Gaussian distribution, to the elite set, updating µ, σ. end for Return the final µ.
26 Cross Entropy Method Sometimes works embarrassingly well
27 Cross Entropy Method Sometimes works embarrassingly well
28 Cross Entropy Method Sometimes works embarrassingly well I. Szita and A. Lörincz. Learning Tetris using the noisy cross-entropy method. Neural computation (2006)
29 Cross Entropy Method Sometimes works embarrassingly well I. Szita and A. Lörincz. Learning Tetris using the noisy cross-entropy method. Neural computation (2006)
30 Stochastic Gradient Ascent on Distribution Let µ define distribution for policy π θ : θ P µ (θ)
31 Stochastic Gradient Ascent on Distribution Let µ define distribution for policy π θ : θ P µ (θ) Return R depends on policy parameter θ and noise ζ maximize E θ,ζ [R(θ, ζ)] µ R is unknown and possibly nondifferentiable
32 Stochastic Gradient Ascent on Distribution Let µ define distribution for policy π θ : θ P µ (θ) Return R depends on policy parameter θ and noise ζ maximize E θ,ζ [R(θ, ζ)] µ R is unknown and possibly nondifferentiable Score function gradient estimator: µ E θ,ζ [R(θ, ζ)] = E θ,ζ [ µ log P µ (θ)r(θ, ζ)] 1 N µ log P µ (θ i )R i N i=1
33 Stochastic Gradient Ascent on Distribution Compare with cross-entropy method
34 Stochastic Gradient Ascent on Distribution Compare with cross-entropy method Score function grad: µ E θ,ζ [R(θ, ζ)] 1 N N µ log P µ (θ i )R i i=1
35 Stochastic Gradient Ascent on Distribution Compare with cross-entropy method Score function grad: µ E θ,ζ [R(θ, ζ)] 1 N N µ log P µ (θ i )R i i=1 Cross entropy method: maximize µ 1 N N log P µ (θ i )f (R i ) i=1 where f (r) = 1[r above threshold] (cross entropy method)
36 Connection to Finite Differences Suppose P µ is Gaussian distribution with mean µ, covariance σ 2 I log P µ (θ) = µ θ 2 /2σ 2 + const µ log P µ (θ) = (θ µ)/σ 2 R i µ log P µ (θ i ) = R i (θ i µ)/σ 2
37 Connection to Finite Differences Suppose P µ is Gaussian distribution with mean µ, covariance σ 2 I log P µ (θ) = µ θ 2 /2σ 2 + const µ log P µ (θ) = (θ µ)/σ 2 R i µ log P µ (θ i ) = R i (θ i µ)/σ 2 Suppose we do antithetic sampling, where we use pairs of samples θ + = µ + σz, θ = µ σz ( ) 1 R(µ + σz, ζ) µ log P µ (θ + ) + R(µ σz, ζ ) µ log P µ (θ ) 2 = 1 σ ( R(µ + σz, ζ) R(µ σz, ζ ) ) z
38 Connection to Finite Differences Suppose P µ is Gaussian distribution with mean µ, covariance σ 2 I log P µ (θ) = µ θ 2 /2σ 2 + const µ log P µ (θ) = (θ µ)/σ 2 R i µ log P µ (θ i ) = R i (θ i µ)/σ 2 Suppose we do antithetic sampling, where we use pairs of samples θ + = µ + σz, θ = µ σz ( ) 1 R(µ + σz, ζ) µ log P µ (θ + ) + R(µ σz, ζ ) µ log P µ (θ ) 2 = 1 σ ( R(µ + σz, ζ) R(µ σz, ζ ) ) z Using same noise ζ for both evaluations reduces variance
39 Deriving the Score Function Estimator Score function gradient estimator: µ E θ,ζ [R(θ, ζ)] = E θ,ζ [ µ log P µ (θ)r(θ, ζ)] 1 N µ log P µ (θ i )R i N i=1
40 Deriving the Score Function Estimator Score function gradient estimator: µ E θ,ζ [R(θ, ζ)] = E θ,ζ [ µ log P µ (θ)r(θ, ζ)] 1 N µ log P µ (θ i )R i N Derive by writing expectation as an integral µ dµdζ P µ (θ)r(θ, ζ) = dµdζ µ P µ (θ)r(θ, ζ) = dµdζ P µ (θ) µ log P µ (θ)r(θ, ζ) i=1 = E θ,ζ [ µ log P µ (θ)r(θ, ζ)]
41 Literature on DFO Evolution strategies (Rechenberg and Eigen, 1973)
42 Literature on DFO Evolution strategies (Rechenberg and Eigen, 1973) Simultaneous perturbation stochastic approximation (Spall, 1992)
43 Literature on DFO Evolution strategies (Rechenberg and Eigen, 1973) Simultaneous perturbation stochastic approximation (Spall, 1992) Covariance matrix adaptation: popular relative of CEM (Hansen, 2006)
44 Literature on DFO Evolution strategies (Rechenberg and Eigen, 1973) Simultaneous perturbation stochastic approximation (Spall, 1992) Covariance matrix adaptation: popular relative of CEM (Hansen, 2006) Reward weighted regression (Peters and Schaal, 2007), PoWER (Kober and Peters, 2007)
45 Success Stories CMA is very effective for optimizing low-dimensional locomotion controllers
46 Success Stories CMA is very effective for optimizing low-dimensional locomotion controllers UT Austin Villa: RoboCup D Simulation League Champion
47 Success Stories CMA is very effective for optimizing low-dimensional locomotion controllers UT Austin Villa: RoboCup D Simulation League Champion Evolution Strategies was shown to perform well on Atari, competetive with policy gradient methods (Salimans et al., 2017)
48 Policy Gradient Methods
49 Overview Problem: maximize E[R π θ ] Here, we ll use a fixed policy parameter θ (instead of sampling θ P µ ) and estimate gradient with respect to θ
50 Overview Problem: maximize E[R π θ ] Here, we ll use a fixed policy parameter θ (instead of sampling θ P µ ) and estimate gradient with respect to θ Noise is in action space rather than parameter space
51 Overview Problem: maximize E[R π θ ] Intuitions: collect a bunch of trajectories, and Make the good trajectories more probable
52 Overview Problem: maximize E[R π θ ] Intuitions: collect a bunch of trajectories, and Make the good trajectories more probable 2. Make the good actions more probable
53 Overview Problem: maximize E[R π θ ] Intuitions: collect a bunch of trajectories, and Make the good trajectories more probable 2. Make the good actions more probable 3. Push the actions towards better actions
54 Score Function Gradient Estimator for Policies Now random variable is a whole trajectory τ = (s 0, a 0, r 0, s 1, a 1, r 1,..., s T 1, a T 1, r T 1, s T ) θ E τ [R(τ)] = E τ [ θ log P(τ θ)r(τ)]
55 Score Function Gradient Estimator for Policies Now random variable is a whole trajectory τ = (s 0, a 0, r 0, s 1, a 1, r 1,..., s T 1, a T 1, r T 1, s T ) Just need to write out P(τ θ): θ E τ [R(τ)] = E τ [ θ log P(τ θ)r(τ)] T 1 P(τ θ) = µ(s 0 ) [π(a t s t, θ)p(s t+1, r t s t, a t )] t=0 T 1 log P(τ θ) = log µ(s 0 ) + [log π(a t s t, θ) + log P(s t+1, r t s t, a t )] t=0 T 1 θ log P(τ θ) = θ log π(a t s t, θ) θ E τ [R] = E τ [ t=0 R θ T 1 ] log π(a t s t, θ) t=0
56 Policy Gradient: Use Temporal Structure Previous slide: [( T 1 )( T 1 )] θ E τ [R] = E τ r t θ log π(a t s t, θ) t=0 t=0
57 Policy Gradient: Use Temporal Structure Previous slide: [( T 1 )( T 1 )] θ E τ [R] = E τ r t θ log π(a t s t, θ) t=0 t=0 We can repeat the same argument to derive the gradient estimator for a single reward term r t. t θ E [r t ] = E r t θ log π(a t s t, θ) t=0
58 Policy Gradient: Use Temporal Structure Previous slide: [( T 1 )( T 1 )] θ E τ [R] = E τ r t θ log π(a t s t, θ) t=0 We can repeat the same argument to derive the gradient estimator for a single reward term r t. t θ E [r t ] = E r t θ log π(a t s t, θ) Sum this formula over t, we obtain T 1 θ E [R] = E = E t=0 [ T 1 t=0 r t t=0 t=0 t θ log π(a t s t, θ) t=0 T 1 θ log π(a t s t, θ) t =t r t ]
59 Policy Gradient: Introduce Baseline Further reduce variance by introducing a baseline b(s) [ T 1 ( T 1 )] θ E τ [R] = E τ θ log π(a t s t, θ) r t b(s t ) t=0 t =t
60 Policy Gradient: Introduce Baseline Further reduce variance by introducing a baseline b(s) [ T 1 ( T 1 )] θ E τ [R] = E τ θ log π(a t s t, θ) r t b(s t ) t=0 t =t For any choice of b, gradient estimator is unbiased.
61 Policy Gradient: Introduce Baseline Further reduce variance by introducing a baseline b(s) [ T 1 ( T 1 )] θ E τ [R] = E τ θ log π(a t s t, θ) r t b(s t ) t=0 For any choice of b, gradient estimator is unbiased. Near optimal choice is expected return, b(s t ) E [r t + r t+1 + r t r T 1 ] t =t
62 Policy Gradient: Introduce Baseline Further reduce variance by introducing a baseline b(s) [ T 1 ( T 1 )] θ E τ [R] = E τ θ log π(a t s t, θ) r t b(s t ) t=0 For any choice of b, gradient estimator is unbiased. Near optimal choice is expected return, b(s t ) E [r t + r t+1 + r t r T 1 ] Interpretation: increase logprob of action a t proportionally to how much returns T 1 t=t r t are better than expected t =t
63 Discounts for Variance Reduction Introduce discount factor γ, which ignores delayed effects between actions and rewards [ T 1 ( T 1 )] θ E τ [R] E τ θ log π(a t s t, θ) γ t t r t b(s t ) t=0 t =t
64 Discounts for Variance Reduction Introduce discount factor γ, which ignores delayed effects between actions and rewards [ T 1 ( T 1 )] θ E τ [R] E τ θ log π(a t s t, θ) γ t t r t b(s t ) t=0 t =t Now, we want b(s t ) E [ r t + γr t+1 + γ 2 r t γ T 1 t r T 1 ]
65 Discounts for Variance Reduction Introduce discount factor γ, which ignores delayed effects between actions and rewards [ T 1 ( T 1 )] θ E τ [R] E τ θ log π(a t s t, θ) γ t t r t b(s t ) t=0 t =t Now, we want b(s t ) E [ ] r t + γr t+1 + γ 2 r t γ T 1 t r T 1 Write gradient estimator more generally as [ T 1 ] θ E τ [R] E τ θ log π(a t s t, θ)ât  t is the advantage estimate t=0
66 Vanilla Policy Gradient Algorithm Initialize policy parameter θ, baseline b for iteration=1, 2,... do Collect a set of trajectories by executing the current policy At each timestep in each trajectory, compute the return ˆR t = T 1 t =t t γt r t, and the advantage estimate  t = ˆR t b(s t ). Re-fit the baseline, by minimizing b(s t ) R t 2, summed over all trajectories and timesteps. Update the policy, using a policy gradient estimate ĝ, which is a sum of terms θ log π(a t s t, θ)ât end for
67 Advantage Actor-Critic Use neural network that represents policy π θ and value function V θ (approximating V π θ) Pseudocode for iteration=1, 2,... do Agent acts for T timesteps (e.g., T = 20), For each timestep t, compute ˆR t = r t + γr t γ T t+1 r T 1 + γ T t V θ (s t )  t = ˆR t V θ (s t ) ˆR t is target value function, in regression problem  t is estimated advantage function T Compute loss gradient g = θ t=1 [ log π θ (a t s t )Ât + c(v θ (s) ˆR ] t ) 2 g is plugged into a stochastic gradient ascent algorithm, e.g., Adam. end for V. Mnih, A. P. Badia, M. Mirza, A. Graves, T. P. Lillicrap, et al. Asynchronous methods for deep reinforcement learning. (2016)
68 Trust Region Policy Optimization Motivation: make policy gradients more robust and sample efficient
69 Trust Region Policy Optimization Motivation: make policy gradients more robust and sample efficient Unlike in supervised learning, policy affects distribution of inputs, so a large bad update can be disastrous
70 Trust Region Policy Optimization Motivation: make policy gradients more robust and sample efficient Unlike in supervised learning, policy affects distribution of inputs, so a large bad update can be disastrous Makes use of a surrogate objective that estimates the performance of the policy around π old used for sampling L πold (π) = 1 N N i=1 π(a i s i ) π old (a i s i )Âi (1) Differentiating this objective gives the policy gradient
71 Trust Region Policy Optimization Motivation: make policy gradients more robust and sample efficient Unlike in supervised learning, policy affects distribution of inputs, so a large bad update can be disastrous Makes use of a surrogate objective that estimates the performance of the policy around π old used for sampling L πold (π) = 1 N N i=1 π(a i s i ) π old (a i s i )Âi (1) Differentiating this objective gives the policy gradient L πold (π) is only accurate when state distribution of π is close to π old, thus it makes sense to constrain or penalize the distance D KL [π old π]
72 Trust Region Policy Optimization Pseudocode: for iteration=1, 2,... do Run policy for T timesteps or N trajectories Estimate advantage function at all timesteps end for maximize θ subject to N n=1 π θ (a n s n ) π θold (a n s n )Ân KL πθold (π θ ) δ Can solve constrained optimization problem efficiently by using conjugate gradient Closely related to natural policy gradients (Kakade, 2002), natural actor critic (Peters and Schaal, 2005), REPS (Peters et al., 2010)
73 Proximal Policy Optimization Use penalty instead of constraint maximize θ N n=1 π θ (a n s n ) π θold (a n s n )Ân C KL πθold (π θ ) Pseudocode: for iteration=1, 2,... do Run policy for T timesteps or N trajectories Estimate advantage function at all timesteps Do SGD on above objective for some number of epochs If KL too high, increase β. If KL too low, decrease β. end for same performance as TRPO, but only first-order optimization
74 Variance Reduction for Policy Gradients
75 Reward Shaping
76 Reward Shaping Reward shaping: δ(s, a, s ) = r(s, a, s ) + γφ(s ) Φ(s) for arbitrary potential Φ 1 A. Y. Ng, D. Harada, and S. Russell. Policy invariance under reward transformations: Theory and application to reward shaping. ICML
77 Reward Shaping Reward shaping: δ(s, a, s ) = r(s, a, s ) + γφ(s ) Φ(s) for arbitrary potential Φ Theorem: δ admits the same optimal policies as r. 1 1 A. Y. Ng, D. Harada, and S. Russell. Policy invariance under reward transformations: Theory and application to reward shaping. ICML
78 Reward Shaping Reward shaping: δ(s, a, s ) = r(s, a, s ) + γφ(s ) Φ(s) for arbitrary potential Φ Theorem: δ admits the same optimal policies as r. 1 Proof sketch: suppose Q satisfies Bellman equation (T Q = Q). If we transform r δ, policy s value function satisfies Q(s, a) = Q (s, a) Φ(s) 1 A. Y. Ng, D. Harada, and S. Russell. Policy invariance under reward transformations: Theory and application to reward shaping. ICML
79 Reward Shaping Reward shaping: δ(s, a, s ) = r(s, a, s ) + γφ(s ) Φ(s) for arbitrary potential Φ Theorem: δ admits the same optimal policies as r. 1 Proof sketch: suppose Q satisfies Bellman equation (T Q = Q). If we transform r δ, policy s value function satisfies Q(s, a) = Q (s, a) Φ(s) Q satisfies Bellman equation Q also satisfies Bellman equation 1 A. Y. Ng, D. Harada, and S. Russell. Policy invariance under reward transformations: Theory and application to reward shaping. ICML
80 Reward Shaping Theorem: δ admits the same optimal policies as R. A. Y. Ng, D. Harada, and S. Russell. Policy invariance under reward transformations: Theory and application to reward shaping. ICML. 1999
81 Reward Shaping Theorem: δ admits the same optimal policies as R. A. Y. Ng, D. Harada, and S. Russell. Policy invariance under reward transformations: Theory and application to reward shaping. ICML Alternative proof: advantage function is invariant. Let s look at effect on V π and Q π : E [ δ 0 + γδ 1 + γ 2 δ ] = E [ (r 0 + γφ(s 1 ) Φ(s 0 )) + γ(r 1 + γφ(s 2 ) Φ(s 1 )) + γ 2 (r 2 + γφ(s 3 ) Φ(s 2 )) +... ] = E [ r 0 + γr 1 + γ 2 r 2 + Φ(s 0 ) ] Thus, A π (s, π(s)) = 0 at all states π is optimal Ṽ π (s) = V π (s) Φ(s) Q π (s) = Q π (s, a) Φ(s) Ã π (s) = A π (s, a)
82 Reward Shaping and Problem Difficulty Shape with Φ = V problem is solved in one step of value iteration
83 Reward Shaping and Problem Difficulty Shape with Φ = V problem is solved in one step of value iteration Shaping leaves policy gradient invariant (and just adds baseline to estimator) E [ θ log π θ (a 0 s 0 )(r 0 + γφ(s 1 ) Φ(s 0 )) + γ(r 1 + γφ(s 2 ) Φ(s 1 )) + γ 2 (r 2 + γφ(s 3 ) Φ(s 2 )) +... ] = E [ θ log π θ (a 0 s 0 )(r 0 + γr 1 + γ 2 r 2 + Φ(s 0 )) ] = E [ θ log π θ (a 0 s 0 )(r 0 + γr 1 + γ 2 r ) ]
84 Reward Shaping and Policy Gradients First note connection between shaped reward and advantage function: E s1 [r 0 + γv π (s 1 ) V π (s 0 ) s 0 = s, a 0 = a] = A π (s, a) Now considering the policy gradient and ignoring all but first shaped reward (i.e., pretend γ = 0 after shaping) we get [ ] [ ] E θ log π θ (a t s t )δ t = E θ log π θ (a t s t )(r t + γv π (s t+1 ) V π (s t )) t [ ] = E θ log π θ (a t s t )A π (s t, a t ) t t
85 Reward Shaping and Policy Gradients Compromise: use more aggressive discount γλ, with λ (0, 1): called generalized advantage estimation θ log π θ (a t s t ) (γλ) k δ t+k t k=0
86 Reward Shaping and Policy Gradients Compromise: use more aggressive discount γλ, with λ (0, 1): called generalized advantage estimation θ log π θ (a t s t ) (γλ) k δ t+k t k=0 Or alternatively, use hard cutoff as in A3C n 1 θ log π θ (a t s t ) γ k δ t+k t = θ log π θ (a t s t ) t k=0 ( n 1 ) γ k r t+k + γ n Φ(s t+n ) Φ(s t ) k=0
87 Reward Shaping Summary Reward shaping transformation leaves policy gradient and optimal policy invariant
88 Reward Shaping Summary Reward shaping transformation leaves policy gradient and optimal policy invariant Shaping with Φ V π makes consequences of actions more immediate
89 Reward Shaping Summary Reward shaping transformation leaves policy gradient and optimal policy invariant Shaping with Φ V π makes consequences of actions more immediate Shaping, and then ignoring all but first term, gives policy gradient
90 Aside: Reward Shaping is Crucial in Practice I. Mordatch, E. Todorov, and Z. Popović. Discovery of complex behaviors through contact-invariant optimization. ACM Transactions on Graphics (TOG) 31.4 (2012), p. 43
91 Aside: Reward Shaping is Crucial in Practice I. Mordatch, E. Todorov, and Z. Popović. Discovery of complex behaviors through contact-invariant optimization. ACM Transactions on Graphics (TOG) 31.4 (2012), p. 43 Y. Tassa, T. Erez, and E. Todorov. Synthesis and stabilization of complex behaviors through online trajectory optimization. Intelligent Robots and Systems (IROS), 2012 IEEE/RSJ International Conference on. IEEE. 2012, pp
92 Choosing parameters γ, λ Performance as γ, λ are varied 0.0 3D Biped cost γ =0.96,λ =0.96 γ =0.98,λ =0.96 γ =0.99,λ =0.96 γ =0.995,λ =0.92 γ =0.995,λ =0.96 γ =0.995,λ =0.98 γ =0.995,λ =0.99 γ =0.995,λ =1.0 γ =1,λ =0.96 γ =1, No value fn number of policy iterations (Generalized Advantage Estimation for Policy Gradients, S. et al., ICLR 2016)
93 Pathwise Derivative Methods
94 Deriving the Policy Gradient, Reparameterized Episodic MDP: θ s 1 s 2... s T a 1 a 2... a T R T Want to compute θ E [R T ]. We ll use θ log π(a t s t ; θ)
95 Deriving the Policy Gradient, Reparameterized Episodic MDP: θ s 1 s 2... s T a 1 a 2... a T R T Want to compute θ E [R T ]. We ll use θ log π(a t s t ; θ) Reparameterize: a t = π(s t, z t ; θ). z t is noise from fixed distribution. θ s 1 s 2... s T a 1 a 2... a T R T z 1 z 2... z T
96 Deriving the Policy Gradient, Reparameterized Episodic MDP: θ s 1 s 2... s T a 1 a 2... a T R T Want to compute θ E [R T ]. We ll use θ log π(a t s t ; θ) Reparameterize: a t = π(s t, z t ; θ). z t is noise from fixed distribution. θ s 1 s 2... s T a 1 a 2... a T R T z 1 z 2... z T Only works if P(s 2 s 1, a 1 ) is known
97 Using a Q-function θ s 1 s 2... s T a 1 a 2... a T R T z 1 z 2... z T [ d dθ E [R T T ] = E = E t=1 [ T t=1 dr T da t da t dθ dq(s t, a t ) da t ] [ T ] d = E E [R T a t ] da t da t=1 t dθ ] [ da t T = E dθ t=1 d dθ Q(s t, π(s t, z t ; θ)) ]
98 SVG(0) Algorithm Learn Q φ to approximate Q π,γ, and use it to compute gradient estimates. N. Heess, G. Wayne, D. Silver, T. Lillicrap, Y. Tassa, et al. Learning Continuous Control Policies by Stochastic Value Gradients. arxiv preprint arxiv: (2015)
99 SVG(0) Algorithm Learn Q φ to approximate Q π,γ, and use it to compute gradient estimates. Pseudocode: for iteration=1, 2,... do Execute policy π θ to collect T timesteps of data Update π θ using g θ T t=1 Q(s t, π(s t, z t ; θ)) Update Q φ using g φ T t=1 (Q φ(s t, a t ) ˆQ t ) 2, e.g. with TD(λ) end for N. Heess, G. Wayne, D. Silver, T. Lillicrap, Y. Tassa, et al. Learning Continuous Control Policies by Stochastic Value Gradients. arxiv preprint arxiv: (2015)
100 SVG(1) Algorithm θ s 1 s 2... s T a 1 a 2... a T R T z 1 z 2... z T Instead of learning Q, we learn
101 SVG(1) Algorithm θ s 1 s 2... s T a 1 a 2... a T R T z 1 z 2... z T Instead of learning Q, we learn State-value function V V π,γ
102 SVG(1) Algorithm θ s 1 s 2... s T a 1 a 2... a T R T z 1 z 2... z T Instead of learning Q, we learn State-value function V V π,γ Dynamics model f, approximating st+1 = f (s t, a t ) + ζ t
103 SVG(1) Algorithm θ s 1 s 2... s T a 1 a 2... a T R T z 1 z 2... z T Instead of learning Q, we learn State-value function V V π,γ Dynamics model f, approximating st+1 = f (s t, a t ) + ζ t Given transition (s t, a t, s t+1 ), infer ζ t = s t+1 f (s t, a t )
104 SVG(1) Algorithm θ s 1 s 2... s T a 1 a 2... a T R T z 1 z 2... z T Instead of learning Q, we learn State-value function V V π,γ Dynamics model f, approximating st+1 = f (s t, a t ) + ζ t Given transition (s t, a t, s t+1 ), infer ζ t = s t+1 f (s t, a t ) Q(s t, a t ) = E [r t + γv (s t+1 )] = E [r t + γv (f (s t, a t ) + ζ t )], and a t = π(s t, θ, ζ t )
105 SVG( ) Algorithm θ s 1 s 2... s T a 1 a 2... a T R T z 1 z 2... z T Just learn dynamics model f
106 SVG( ) Algorithm θ s 1 s 2... s T a 1 a 2... a T R T z 1 z 2... z T Just learn dynamics model f Given whole trajectory, infer all noise variables
107 SVG( ) Algorithm θ s 1 s 2... s T a 1 a 2... a T R T z 1 z 2... z T Just learn dynamics model f Given whole trajectory, infer all noise variables Freeze all policy and dynamics noise, differentiate through entire deterministic computation graph
108 SVG Results Applied to 2D robotics tasks N. Heess, G. Wayne, D. Silver, T. Lillicrap, Y. Tassa, et al. Learning Continuous Control Policies by Stochastic Value Gradients. arxiv preprint arxiv: (2015)
109 SVG Results Applied to 2D robotics tasks Overall: different gradient estimators behave similarly N. Heess, G. Wayne, D. Silver, T. Lillicrap, Y. Tassa, et al. Learning Continuous Control Policies by Stochastic Value Gradients. arxiv preprint arxiv: (2015)
110 Deterministic Policy Gradient For Gaussian actions, variance of score function policy gradient estimator goes to infinity as variance goes to zero D. Silver, G. Lever, N. Heess, T. Degris, D. Wierstra, et al. Deterministic Policy Gradient Algorithms. ICML. 2014
111 Deterministic Policy Gradient For Gaussian actions, variance of score function policy gradient estimator goes to infinity as variance goes to zero Intuition: finite difference gradient estimators D. Silver, G. Lever, N. Heess, T. Degris, D. Wierstra, et al. Deterministic Policy Gradient Algorithms. ICML. 2014
112 Deterministic Policy Gradient For Gaussian actions, variance of score function policy gradient estimator goes to infinity as variance goes to zero Intuition: finite difference gradient estimators But SVG(0) gradient is fine when σ 0 θ Q(s t, π(s t, θ, ζ t )) t D. Silver, G. Lever, N. Heess, T. Degris, D. Wierstra, et al. Deterministic Policy Gradient Algorithms. ICML. 2014
113 Deterministic Policy Gradient For Gaussian actions, variance of score function policy gradient estimator goes to infinity as variance goes to zero Intuition: finite difference gradient estimators But SVG(0) gradient is fine when σ 0 θ Q(s t, π(s t, θ, ζ t )) Problem: there s no exploration. t D. Silver, G. Lever, N. Heess, T. Degris, D. Wierstra, et al. Deterministic Policy Gradient Algorithms. ICML. 2014
114 Deterministic Policy Gradient For Gaussian actions, variance of score function policy gradient estimator goes to infinity as variance goes to zero Intuition: finite difference gradient estimators But SVG(0) gradient is fine when σ 0 θ Q(s t, π(s t, θ, ζ t )) Problem: there s no exploration. t Solution: add noise to the policy, but estimate Q with TD(0), so it s valid off-policy D. Silver, G. Lever, N. Heess, T. Degris, D. Wierstra, et al. Deterministic Policy Gradient Algorithms. ICML. 2014
115 Deterministic Policy Gradient For Gaussian actions, variance of score function policy gradient estimator goes to infinity as variance goes to zero Intuition: finite difference gradient estimators But SVG(0) gradient is fine when σ 0 θ Q(s t, π(s t, θ, ζ t )) Problem: there s no exploration. t Solution: add noise to the policy, but estimate Q with TD(0), so it s valid off-policy Policy gradient is a little biased (even with Q = Q π ), but only because state distribution is off it gets the right gradient at every state D. Silver, G. Lever, N. Heess, T. Degris, D. Wierstra, et al. Deterministic Policy Gradient Algorithms. ICML. 2014
116 Deep Deterministic Policy Gradient Incorporate replay buffer and target network ideas from DQN for increased stability Use lagged (Polyak-averaging) version of Q φ and π θ for fitting Q φ (towards Q π,γ ) with TD(0) ˆQ t = r t + γq φ (s t+1, π(s t+1 ; θ )) Pseudocode: for iteration=1, 2,... do Act for several timesteps, add data to replay buffer Sample minibatch Update π θ using g θ T t=1 Q(s t, π(s t, z t ; θ)) Update Q φ using g φ T t=1 (Q φ(s t, a t ) ˆQ t ) 2, end for T. P. Lillicrap, J. J. Hunt, A. Pritzel, N. Heess, T. Erez, et al. Continuous control with deep reinforcement learning. arxiv preprint arxiv: (2015)
117 DDPG Results Applied to 2D and 3D robotics tasks and driving with pixel input T. P. Lillicrap, J. J. Hunt, A. Pritzel, N. Heess, T. Erez, et al. Continuous control with deep reinforcement learning. arxiv preprint arxiv: (2015)
118 Policy Gradient Methods: Comparison Two kinds of policy gradient estimator
119 Policy Gradient Methods: Comparison Two kinds of policy gradient estimator REINFORCE / score function estimator: log π(a s) Â.
120 Policy Gradient Methods: Comparison Two kinds of policy gradient estimator REINFORCE / score function estimator: log π(a s) Â. Learn Q or V for variance reduction, to estimate Â
121 Policy Gradient Methods: Comparison Two kinds of policy gradient estimator REINFORCE / score function estimator: log π(a s) Â. Learn Q or V for variance reduction, to estimate  Pathwise derivative estimators (differentiate wrt action)
122 Policy Gradient Methods: Comparison Two kinds of policy gradient estimator REINFORCE / score function estimator: log π(a s) Â. Learn Q or V for variance reduction, to estimate  Pathwise derivative estimators (differentiate wrt action) SVG(0) / DPG: d da Q(s, a) (learn Q)
123 Policy Gradient Methods: Comparison Two kinds of policy gradient estimator REINFORCE / score function estimator: log π(a s) Â. Learn Q or V for variance reduction, to estimate  Pathwise derivative estimators (differentiate wrt action) SVG(0) / DPG: d da Q(s, a) (learn Q) SVG(1): d da (r + γv (s )) (learn f, V )
124 Policy Gradient Methods: Comparison Two kinds of policy gradient estimator REINFORCE / score function estimator: log π(a s) Â. Learn Q or V for variance reduction, to estimate  Pathwise derivative estimators (differentiate wrt action) SVG(0) / DPG: d da Q(s, a) (learn Q) SVG(1): d da (r + γv (s )) (learn f, V ) d SVG( ): da t (r t + γr t+1 + γ 2 r t ) (learn f )
125 Policy Gradient Methods: Comparison Two kinds of policy gradient estimator REINFORCE / score function estimator: log π(a s) Â. Learn Q or V for variance reduction, to estimate  Pathwise derivative estimators (differentiate wrt action) SVG(0) / DPG: d da Q(s, a) (learn Q) SVG(1): d da (r + γv (s )) (learn f, V ) d SVG( ): da t (r t + γr t+1 + γ 2 r t ) (learn f ) Pathwise derivative methods more sample-efficient when they work (maybe), but work less generally due to high bias
126 Thanks Questions?
Variance Reduction for Policy Gradient Methods. March 13, 2017
Variance Reduction for Policy Gradient Methods March 13, 2017 Reward Shaping Reward Shaping Reward Shaping Reward shaping: r(s, a, s ) = r(s, a, s ) + γφ(s ) Φ(s) for arbitrary potential Φ Theorem: r admits
More informationPolicy Gradient Methods. February 13, 2017
Policy Gradient Methods February 13, 2017 Policy Optimization Problems maximize E π [expression] π Fixed-horizon episodic: T 1 Average-cost: lim T 1 T r t T 1 r t Infinite-horizon discounted: γt r t Variable-length
More informationDeep Reinforcement Learning: Policy Gradients and Q-Learning
Deep Reinforcement Learning: Policy Gradients and Q-Learning John Schulman Bay Area Deep Learning School September 24, 2016 Introduction and Overview Aim of This Talk What is deep RL, and should I use
More informationDeep Reinforcement Learning
Deep Reinforcement Learning John Schulman 1 MLSS, May 2016, Cadiz 1 Berkeley Artificial Intelligence Research Lab Agenda Introduction and Overview Markov Decision Processes Reinforcement Learning via Black-Box
More informationLecture 9: Policy Gradient II 1
Lecture 9: Policy Gradient II 1 Emma Brunskill CS234 Reinforcement Learning. Winter 2019 Additional reading: Sutton and Barto 2018 Chp. 13 1 With many slides from or derived from David Silver and John
More informationLecture 9: Policy Gradient II (Post lecture) 2
Lecture 9: Policy Gradient II (Post lecture) 2 Emma Brunskill CS234 Reinforcement Learning. Winter 2018 Additional reading: Sutton and Barto 2018 Chp. 13 2 With many slides from or derived from David Silver
More informationLecture 8: Policy Gradient I 2
Lecture 8: Policy Gradient I 2 Emma Brunskill CS234 Reinforcement Learning. Winter 2018 Additional reading: Sutton and Barto 2018 Chp. 13 2 With many slides from or derived from David Silver and John Schulman
More informationReinforcement Learning and NLP
1 Reinforcement Learning and NLP Kapil Thadani kapil@cs.columbia.edu RESEARCH Outline 2 Model-free RL Markov decision processes (MDPs) Derivative-free optimization Policy gradients Variance reduction Value
More informationReinforcement Learning
Reinforcement Learning Policy Search: Actor-Critic and Gradient Policy search Mario Martin CS-UPC May 28, 2018 Mario Martin (CS-UPC) Reinforcement Learning May 28, 2018 / 63 Goal of this lecture So far
More informationTrust Region Policy Optimization
Trust Region Policy Optimization Yixin Lin Duke University yixin.lin@duke.edu March 28, 2017 Yixin Lin (Duke) TRPO March 28, 2017 1 / 21 Overview 1 Preliminaries Markov Decision Processes Policy iteration
More informationReinforcement Learning via Policy Optimization
Reinforcement Learning via Policy Optimization Hanxiao Liu November 22, 2017 1 / 27 Reinforcement Learning Policy a π(s) 2 / 27 Example - Mario 3 / 27 Example - ChatBot 4 / 27 Applications - Video Games
More informationAdvanced Policy Gradient Methods: Natural Gradient, TRPO, and More. March 8, 2017
Advanced Policy Gradient Methods: Natural Gradient, TRPO, and More March 8, 2017 Defining a Loss Function for RL Let η(π) denote the expected return of π [ ] η(π) = E s0 ρ 0,a t π( s t) γ t r t We collect
More informationReinforcement Learning
Reinforcement Learning Policy gradients Daniel Hennes 26.06.2017 University Stuttgart - IPVS - Machine Learning & Robotics 1 Policy based reinforcement learning So far we approximated the action value
More informationarxiv: v5 [cs.lg] 9 Sep 2016
HIGH-DIMENSIONAL CONTINUOUS CONTROL USING GENERALIZED ADVANTAGE ESTIMATION John Schulman, Philipp Moritz, Sergey Levine, Michael I. Jordan and Pieter Abbeel Department of Electrical Engineering and Computer
More informationDeep reinforcement learning. Dialogue Systems Group, Cambridge University Engineering Department
Deep reinforcement learning Milica Gašić Dialogue Systems Group, Cambridge University Engineering Department 1 / 25 In this lecture... Introduction to deep reinforcement learning Value-based Deep RL Deep
More informationDeterministic Policy Gradient, Advanced RL Algorithms
NPFL122, Lecture 9 Deterministic Policy Gradient, Advanced RL Algorithms Milan Straka December 1, 218 Charles University in Prague Faculty of Mathematics and Physics Institute of Formal and Applied Linguistics
More informationLecture 8: Policy Gradient
Lecture 8: Policy Gradient Hado van Hasselt Outline 1 Introduction 2 Finite Difference Policy Gradient 3 Monte-Carlo Policy Gradient 4 Actor-Critic Policy Gradient Introduction Vapnik s rule Never solve
More informationINF 5860 Machine learning for image classification. Lecture 14: Reinforcement learning May 9, 2018
Machine learning for image classification Lecture 14: Reinforcement learning May 9, 2018 Page 3 Outline Motivation Introduction to reinforcement learning (RL) Value function based methods (Q-learning)
More informationQ-Learning in Continuous State Action Spaces
Q-Learning in Continuous State Action Spaces Alex Irpan alexirpan@berkeley.edu December 5, 2015 Contents 1 Introduction 1 2 Background 1 3 Q-Learning 2 4 Q-Learning In Continuous Spaces 4 5 Experimental
More informationO P T I M I Z I N G E X P E C TAT I O N S : T O S T O C H A S T I C C O M P U TAT I O N G R A P H S. john schulman. Summer, 2016
O P T I M I Z I N G E X P E C TAT I O N S : FROM DEEP REINFORCEMENT LEARNING T O S T O C H A S T I C C O M P U TAT I O N G R A P H S john schulman Summer, 2016 A dissertation submitted in partial satisfaction
More informationReinforcement Learning for NLP
Reinforcement Learning for NLP Advanced Machine Learning for NLP Jordan Boyd-Graber REINFORCEMENT OVERVIEW, POLICY GRADIENT Adapted from slides by David Silver, Pieter Abbeel, and John Schulman Advanced
More informationREINFORCE Framework for Stochastic Policy Optimization and its use in Deep Learning
REINFORCE Framework for Stochastic Policy Optimization and its use in Deep Learning Ronen Tamari The Hebrew University of Jerusalem Advanced Seminar in Deep Learning (#67679) February 28, 2016 Ronen Tamari
More informationReinforcement Learning
Reinforcement Learning From the basics to Deep RL Olivier Sigaud ISIR, UPMC + INRIA http://people.isir.upmc.fr/sigaud September 14, 2017 1 / 54 Introduction Outline Some quick background about discrete
More informationComparing Deep Reinforcement Learning and Evolutionary Methods in Continuous Control
Comparing Deep Reinforcement Learning and Evolutionary Methods in Continuous Control Shangtong Zhang Dept. of Computing Science University of Alberta shangtong.zhang@ualberta.ca Osmar R. Zaiane Dept. of
More informationREINFORCEMENT LEARNING
REINFORCEMENT LEARNING Larry Page: Where s Google going next? DeepMind's DQN playing Breakout Contents Introduction to Reinforcement Learning Deep Q-Learning INTRODUCTION TO REINFORCEMENT LEARNING Contents
More information15-889e Policy Search: Gradient Methods Emma Brunskill. All slides from David Silver (with EB adding minor modificafons), unless otherwise noted
15-889e Policy Search: Gradient Methods Emma Brunskill All slides from David Silver (with EB adding minor modificafons), unless otherwise noted Outline 1 Introduction 2 Finite Difference Policy Gradient
More informationCSC321 Lecture 22: Q-Learning
CSC321 Lecture 22: Q-Learning Roger Grosse Roger Grosse CSC321 Lecture 22: Q-Learning 1 / 21 Overview Second of 3 lectures on reinforcement learning Last time: policy gradient (e.g. REINFORCE) Optimize
More informationDeep Reinforcement Learning SISL. Jeremy Morton (jmorton2) November 7, Stanford Intelligent Systems Laboratory
Deep Reinforcement Learning Jeremy Morton (jmorton2) November 7, 2016 SISL Stanford Intelligent Systems Laboratory Overview 2 1 Motivation 2 Neural Networks 3 Deep Reinforcement Learning 4 Deep Learning
More informationDueling Network Architectures for Deep Reinforcement Learning (ICML 2016)
Dueling Network Architectures for Deep Reinforcement Learning (ICML 2016) Yoonho Lee Department of Computer Science and Engineering Pohang University of Science and Technology October 11, 2016 Outline
More informationOptimizing Expectations: From Deep Reinforcement Learning to Stochastic Computation Graphs
Optimizing Expectations: From Deep Reinforcement Learning to Stochastic Computation Graphs John Schulman Electrical Engineering and Computer Sciences University of California at Berkeley Technical Report
More informationUsing Gaussian Processes for Variance Reduction in Policy Gradient Algorithms *
Proceedings of the 8 th International Conference on Applied Informatics Eger, Hungary, January 27 30, 2010. Vol. 1. pp. 87 94. Using Gaussian Processes for Variance Reduction in Policy Gradient Algorithms
More information(Deep) Reinforcement Learning
Martin Matyášek Artificial Intelligence Center Czech Technical University in Prague October 27, 2016 Martin Matyášek VPD, 2016 1 / 17 Reinforcement Learning in a picture R. S. Sutton and A. G. Barto 2015
More informationReinforcement Learning
Reinforcement Learning Model-Based Reinforcement Learning Model-based, PAC-MDP, sample complexity, exploration/exploitation, RMAX, E3, Bayes-optimal, Bayesian RL, model learning Vien Ngo MLR, University
More informationIntroduction to Reinforcement Learning. CMPT 882 Mar. 18
Introduction to Reinforcement Learning CMPT 882 Mar. 18 Outline for the week Basic ideas in RL Value functions and value iteration Policy evaluation and policy improvement Model-free RL Monte-Carlo and
More informationGeneralized Advantage Estimation for Policy Gradients
Generalized Advantage Estimation for Policy Gradients Authors Department of Electrical Engineering and Computer Science Abstract Value functions provide an elegant solution to the delayed reward problem
More informationMultiagent (Deep) Reinforcement Learning
Multiagent (Deep) Reinforcement Learning MARTIN PILÁT (MARTIN.PILAT@MFF.CUNI.CZ) Reinforcement learning The agent needs to learn to perform tasks in environment No prior knowledge about the effects of
More informationGradient Estimation Using Stochastic Computation Graphs
Gradient Estimation Using Stochastic Computation Graphs Yoonho Lee Department of Computer Science and Engineering Pohang University of Science and Technology May 9, 2017 Outline Stochastic Gradient Estimation
More informationarxiv: v2 [cs.lg] 7 Mar 2018
Comparing Deep Reinforcement Learning and Evolutionary Methods in Continuous Control arxiv:1712.00006v2 [cs.lg] 7 Mar 2018 Shangtong Zhang 1, Osmar R. Zaiane 2 12 Dept. of Computing Science, University
More informationForward Actor-Critic for Nonlinear Function Approximation in Reinforcement Learning
Forward Actor-Critic for Nonlinear Function Approximation in Reinforcement Learning Vivek Veeriah Dept. of Computing Science University of Alberta Edmonton, Canada vivekveeriah@ualberta.ca Harm van Seijen
More informationSoft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor Tuomas Haarnoja, Aurick Zhou, Pieter Abbeel & Sergey Levine Department of Electrical Engineering and Computer
More informationMarkov Decision Processes and Solving Finite Problems. February 8, 2017
Markov Decision Processes and Solving Finite Problems February 8, 2017 Overview of Upcoming Lectures Feb 8: Markov decision processes, value iteration, policy iteration Feb 13: Policy gradients Feb 15:
More informationMulti-Batch Experience Replay for Fast Convergence of Continuous Action Control
1 Multi-Batch Experience Replay for Fast Convergence of Continuous Action Control Seungyul Han and Youngchul Sung Abstract arxiv:1710.04423v1 [cs.lg] 12 Oct 2017 Policy gradient methods for direct policy
More informationLearning Control for Air Hockey Striking using Deep Reinforcement Learning
Learning Control for Air Hockey Striking using Deep Reinforcement Learning Ayal Taitler, Nahum Shimkin Faculty of Electrical Engineering Technion - Israel Institute of Technology May 8, 2017 A. Taitler,
More informationarxiv: v2 [cs.lg] 8 Aug 2018
: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor Tuomas Haarnoja 1 Aurick Zhou 1 Pieter Abbeel 1 Sergey Levine 1 arxiv:181.129v2 [cs.lg] 8 Aug 218 Abstract Model-free deep
More informationDavid Silver, Google DeepMind
Tutorial: Deep Reinforcement Learning David Silver, Google DeepMind Outline Introduction to Deep Learning Introduction to Reinforcement Learning Value-Based Deep RL Policy-Based Deep RL Model-Based Deep
More informationReinforcement. Function Approximation. Learning with KATJA HOFMANN. Researcher, MSR Cambridge
Reinforcement Learning with Function Approximation KATJA HOFMANN Researcher, MSR Cambridge Representation and Generalization in RL Focus on training stability Learning generalizable value functions Navigating
More informationDecision Theory: Q-Learning
Decision Theory: Q-Learning CPSC 322 Decision Theory 5 Textbook 12.5 Decision Theory: Q-Learning CPSC 322 Decision Theory 5, Slide 1 Lecture Overview 1 Recap 2 Asynchronous Value Iteration 3 Q-Learning
More informationDeep Reinforcement Learning. Scratching the surface
Deep Reinforcement Learning Scratching the surface Deep Reinforcement Learning Scenario of Reinforcement Learning Observation State Agent Action Change the environment Don t do that Reward Environment
More informationTemporal Difference. Learning KENNETH TRAN. Principal Research Engineer, MSR AI
Temporal Difference Learning KENNETH TRAN Principal Research Engineer, MSR AI Temporal Difference Learning Policy Evaluation Intro to model-free learning Monte Carlo Learning Temporal Difference Learning
More informationReinforcement learning
Reinforcement learning Stuart Russell, UC Berkeley Stuart Russell, UC Berkeley 1 Outline Sequential decision making Dynamic programming algorithms Reinforcement learning algorithms temporal difference
More informationIntroduction to Reinforcement Learning
CSCI-699: Advanced Topics in Deep Learning 01/16/2019 Nitin Kamra Spring 2019 Introduction to Reinforcement Learning 1 What is Reinforcement Learning? So far we have seen unsupervised and supervised learning.
More informationProximal Policy Optimization Algorithms
Proximal Policy Optimization Algorithms John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, Oleg Klimov OpenAI {joschu, filip, prafulla, alec, oleg}@openai.com arxiv:177.6347v2 [cs.lg] 28 Aug
More informationCS230: Lecture 9 Deep Reinforcement Learning
CS230: Lecture 9 Deep Reinforcement Learning Kian Katanforoosh Menti code: 21 90 15 Today s outline I. Motivation II. Recycling is good: an introduction to RL III. Deep Q-Learning IV. Application of Deep
More informationReal Time Value Iteration and the State-Action Value Function
MS&E338 Reinforcement Learning Lecture 3-4/9/18 Real Time Value Iteration and the State-Action Value Function Lecturer: Ben Van Roy Scribe: Apoorva Sharma and Tong Mu 1 Review Last time we left off discussing
More informationLearning Dexterity Matthias Plappert SEPTEMBER 6, 2018
Learning Dexterity Matthias Plappert SEPTEMBER 6, 2018 OpenAI OpenAI is a non-profit AI research company, discovering and enacting the path to safe artificial general intelligence. OpenAI OpenAI is a non-profit
More informationReinforcement Learning. Donglin Zeng, Department of Biostatistics, University of North Carolina
Reinforcement Learning Introduction Introduction Unsupervised learning has no outcome (no feedback). Supervised learning has outcome so we know what to predict. Reinforcement learning is in between it
More informationGrundlagen der Künstlichen Intelligenz
Grundlagen der Künstlichen Intelligenz Reinforcement learning Daniel Hennes 4.12.2017 (WS 2017/18) University Stuttgart - IPVS - Machine Learning & Robotics 1 Today Reinforcement learning Model based and
More informationMARKOV DECISION PROCESSES (MDP) AND REINFORCEMENT LEARNING (RL) Versione originale delle slide fornita dal Prof. Francesco Lo Presti
1 MARKOV DECISION PROCESSES (MDP) AND REINFORCEMENT LEARNING (RL) Versione originale delle slide fornita dal Prof. Francesco Lo Presti Historical background 2 Original motivation: animal learning Early
More informationCombining PPO and Evolutionary Strategies for Better Policy Search
Combining PPO and Evolutionary Strategies for Better Policy Search Jennifer She 1 Abstract A good policy search algorithm needs to strike a balance between being able to explore candidate policies and
More informationReinforcement Learning
Reinforcement Learning Temporal Difference Learning Temporal difference learning, TD prediction, Q-learning, elibigility traces. (many slides from Marc Toussaint) Vien Ngo MLR, University of Stuttgart
More informationLecture 1: March 7, 2018
Reinforcement Learning Spring Semester, 2017/8 Lecture 1: March 7, 2018 Lecturer: Yishay Mansour Scribe: ym DISCLAIMER: Based on Learning and Planning in Dynamical Systems by Shie Mannor c, all rights
More informationReinforcement Learning. Spring 2018 Defining MDPs, Planning
Reinforcement Learning Spring 2018 Defining MDPs, Planning understandability 0 Slide 10 time You are here Markov Process Where you will go depends only on where you are Markov Process: Information state
More informationReinforcement Learning as Variational Inference: Two Recent Approaches
Reinforcement Learning as Variational Inference: Two Recent Approaches Rohith Kuditipudi Duke University 11 August 2017 Outline 1 Background 2 Stein Variational Policy Gradient 3 Soft Q-Learning 4 Closing
More informationarxiv: v2 [cs.lg] 2 Oct 2018
AMBER: Adaptive Multi-Batch Experience Replay for Continuous Action Control arxiv:171.4423v2 [cs.lg] 2 Oct 218 Seungyul Han Dept. of Electrical Engineering KAIST Daejeon, South Korea 34141 sy.han@kaist.ac.kr
More informationCOMP9444 Neural Networks and Deep Learning 10. Deep Reinforcement Learning. COMP9444 c Alan Blair, 2017
COMP9444 Neural Networks and Deep Learning 10. Deep Reinforcement Learning COMP9444 17s2 Deep Reinforcement Learning 1 Outline History of Reinforcement Learning Deep Q-Learning for Atari Games Actor-Critic
More informationLecture 23: Reinforcement Learning
Lecture 23: Reinforcement Learning MDPs revisited Model-based learning Monte Carlo value function estimation Temporal-difference (TD) learning Exploration November 23, 2006 1 COMP-424 Lecture 23 Recall:
More informationActor-critic methods. Dialogue Systems Group, Cambridge University Engineering Department. February 21, 2017
Actor-critic methods Milica Gašić Dialogue Systems Group, Cambridge University Engineering Department February 21, 2017 1 / 21 In this lecture... The actor-critic architecture Least-Squares Policy Iteration
More informationDecision Theory: Markov Decision Processes
Decision Theory: Markov Decision Processes CPSC 322 Lecture 33 March 31, 2006 Textbook 12.5 Decision Theory: Markov Decision Processes CPSC 322 Lecture 33, Slide 1 Lecture Overview Recap Rewards and Policies
More informationLecture 7: Value Function Approximation
Lecture 7: Value Function Approximation Joseph Modayil Outline 1 Introduction 2 3 Batch Methods Introduction Large-Scale Reinforcement Learning Reinforcement learning can be used to solve large problems,
More informationMachine Learning I Continuous Reinforcement Learning
Machine Learning I Continuous Reinforcement Learning Thomas Rückstieß Technische Universität München January 7/8, 2010 RL Problem Statement (reminder) state s t+1 ENVIRONMENT reward r t+1 new step r t
More information1 Introduction 2. 4 Q-Learning The Q-value The Temporal Difference The whole Q-Learning process... 5
Table of contents 1 Introduction 2 2 Markov Decision Processes 2 3 Future Cumulative Reward 3 4 Q-Learning 4 4.1 The Q-value.............................................. 4 4.2 The Temporal Difference.......................................
More informationReinforcement Learning
Reinforcement Learning Function approximation Daniel Hennes 19.06.2017 University Stuttgart - IPVS - Machine Learning & Robotics 1 Today Eligibility traces n-step TD returns Forward and backward view Function
More informationIntroduction of Reinforcement Learning
Introduction of Reinforcement Learning Deep Reinforcement Learning Reference Textbook: Reinforcement Learning: An Introduction http://incompleteideas.net/sutton/book/the-book.html Lectures of David Silver
More informationReinforcement Learning
Reinforcement Learning Function approximation Mario Martin CS-UPC May 18, 2018 Mario Martin (CS-UPC) Reinforcement Learning May 18, 2018 / 65 Recap Algorithms: MonteCarlo methods for Policy Evaluation
More informationarxiv: v4 [cs.lg] 14 Oct 2018
Equivalence Between Policy Gradients and Soft -Learning John Schulman 1, Xi Chen 1,2, and Pieter Abbeel 1,2 1 OpenAI 2 UC Berkeley, EECS Dept. {joschu, peter, pieter}@openai.com arxiv:174.644v4 cs.lg 14
More informationReinforcement Learning and Deep Reinforcement Learning
Reinforcement Learning and Deep Reinforcement Learning Ashis Kumer Biswas, Ph.D. ashis.biswas@ucdenver.edu Deep Learning November 5, 2018 1 / 64 Outlines 1 Principles of Reinforcement Learning 2 The Q
More informationLearning Continuous Control Policies by Stochastic Value Gradients
Learning Continuous Control Policies by Stochastic Value Gradients Nicolas Heess, Greg Wayne, David Silver, Timothy Lillicrap, Yuval Tassa, Tom Erez Google DeepMind {heess, gregwayne, davidsilver, countzero,
More informationReinforcement Learning. Yishay Mansour Tel-Aviv University
Reinforcement Learning Yishay Mansour Tel-Aviv University 1 Reinforcement Learning: Course Information Classes: Wednesday Lecture 10-13 Yishay Mansour Recitations:14-15/15-16 Eliya Nachmani Adam Polyak
More informationReinforcement Learning
Reinforcement Learning RL in continuous MDPs March April, 2015 Large/Continuous MDPs Large/Continuous state space Tabular representation cannot be used Large/Continuous action space Maximization over action
More informationLecture 25: Learning 4. Victor R. Lesser. CMPSCI 683 Fall 2010
Lecture 25: Learning 4 Victor R. Lesser CMPSCI 683 Fall 2010 Final Exam Information Final EXAM on Th 12/16 at 4:00pm in Lederle Grad Res Ctr Rm A301 2 Hours but obviously you can leave early! Open Book
More information15-780: ReinforcementLearning
15-780: ReinforcementLearning J. Zico Kolter March 2, 2016 1 Outline Challenge of RL Model-based methods Model-free methods Exploration and exploitation 2 Outline Challenge of RL Model-based methods Model-free
More informationLecture 10 - Planning under Uncertainty (III)
Lecture 10 - Planning under Uncertainty (III) Jesse Hoey School of Computer Science University of Waterloo March 27, 2018 Readings: Poole & Mackworth (2nd ed.)chapter 12.1,12.3-12.9 1/ 34 Reinforcement
More informationReinforcement Learning
Reinforcement Learning Function Approximation Continuous state/action space, mean-square error, gradient temporal difference learning, least-square temporal difference, least squares policy iteration Vien
More informationTowards Generalization and Simplicity in Continuous Control
Towards Generalization and Simplicity in Continuous Control Aravind Rajeswaran, Kendall Lowrey, Emanuel Todorov, Sham Kakade Paul Allen School of Computer Science University of Washington Seattle { aravraj,
More informationBehavior Policy Gradient Supplemental Material
Behavior Policy Gradient Supplemental Material Josiah P. Hanna 1 Philip S. Thomas 2 3 Peter Stone 1 Scott Niekum 1 A. Proof of Theorem 1 In Appendix A, we give the full derivation of our primary theoretical
More informationAn Off-policy Policy Gradient Theorem Using Emphatic Weightings
An Off-policy Policy Gradient Theorem Using Emphatic Weightings Ehsan Imani, Eric Graves, Martha White Reinforcement Learning and Artificial Intelligence Laboratory Department of Computing Science University
More informationReinforcement Learning with Function Approximation. Joseph Christian G. Noel
Reinforcement Learning with Function Approximation Joseph Christian G. Noel November 2011 Abstract Reinforcement learning (RL) is a key problem in the field of Artificial Intelligence. The main goal is
More informationarxiv: v1 [cs.lg] 30 Oct 2015
Learning Continuous Control Policies by Stochastic Value Gradients arxiv:1510.09142v1 cs.lg 30 Oct 2015 Nicolas Heess, Greg Wayne, David Silver, Timothy Lillicrap, Yuval Tassa, Tom Erez Google DeepMind
More informationDecoupling deep learning and reinforcement learning for stable and efficient deep policy gradient algorithms
Decoupling deep learning and reinforcement learning for stable and efficient deep policy gradient algorithms Alfredo Vicente Clemente Master of Science in Computer Science Submission date: August 2017
More informationNonparametric Inverse Reinforcement Learning and Approximate Optimal Control with Temporal Logic Tasks. Siddharthan Rajasekaran
Nonparametric Inverse Reinforcement Learning and Approximate Optimal Control with Temporal Logic Tasks by Siddharthan Rajasekaran A dissertation submitted in partial satisfaction of the requirements for
More informationReinforcement Learning II. George Konidaris
Reinforcement Learning II George Konidaris gdk@cs.brown.edu Fall 2017 Reinforcement Learning π : S A max R = t=0 t r t MDPs Agent interacts with an environment At each time t: Receives sensor signal Executes
More informationVariational Deep Q Network
Variational Deep Q Network Yunhao Tang Department of IEOR Columbia University yt2541@columbia.edu Alp Kucukelbir Department of Computer Science Columbia University alp@cs.columbia.edu Abstract We propose
More informationReinforcement Learning: the basics
Reinforcement Learning: the basics Olivier Sigaud Université Pierre et Marie Curie, PARIS 6 http://people.isir.upmc.fr/sigaud August 6, 2012 1 / 46 Introduction Action selection/planning Learning by trial-and-error
More informationELEC-E8119 Robotics: Manipulation, Decision Making and Learning Policy gradient approaches. Ville Kyrki
ELEC-E8119 Robotics: Manipulation, Decision Making and Learning Policy gradient approaches Ville Kyrki 9.10.2017 Today Direct policy learning via policy gradient. Learning goals Understand basis and limitations
More informationHuman-level control through deep reinforcement. Liia Butler
Humanlevel control through deep reinforcement Liia Butler But first... A quote "The question of whether machines can think... is about as relevant as the question of whether submarines can swim" Edsger
More informationReinforcement Learning II. George Konidaris
Reinforcement Learning II George Konidaris gdk@cs.brown.edu Fall 2018 Reinforcement Learning π : S A max R = t=0 t r t MDPs Agent interacts with an environment At each time t: Receives sensor signal Executes
More informationTrust Region Evolution Strategies
Trust Region Evolution Strategies Guoqing Liu, Li Zhao, Feidiao Yang, Jiang Bian, Tao Qin, Nenghai Yu, Tie-Yan Liu University of Science and Technology of China Microsoft Research Institute of Computing
More informationReinforcement Learning
Reinforcement Learning Cyber Rodent Project Some slides from: David Silver, Radford Neal CSC411: Machine Learning and Data Mining, Winter 2017 Michael Guerzhoy 1 Reinforcement Learning Supervised learning:
More informationApproximate Q-Learning. Dan Weld / University of Washington
Approximate Q-Learning Dan Weld / University of Washington [Many slides taken from Dan Klein and Pieter Abbeel / CS188 Intro to AI at UC Berkeley materials available at http://ai.berkeley.edu.] Q Learning
More informationTutorial on Policy Gradient Methods. Jan Peters
Tutorial on Policy Gradient Methods Jan Peters Outline 1. Reinforcement Learning 2. Finite Difference vs Likelihood-Ratio Policy Gradients 3. Likelihood-Ratio Policy Gradients 4. Conclusion General Setup
More information