Finite-Sample Analysis in Reinforcement Learning
|
|
- Henry Floyd
- 5 years ago
- Views:
Transcription
1 Finite-Sample Analysis in Reinforcement Learning Mohammad Ghavamzadeh INRIA Lille Nord Europe, Team SequeL
2 Outline 1 Introduction to RL and DP 2 Approximate Dynamic Programming (AVI & API) 3 How does Statistical Learning Theory come to the picture? 4 Error Propagation (AVI & API Error Propagation) 5 An AVI Algorithm (Fitted Q-Iteration) FQI: error at each iteration Final performance bound of FQI 6 An API Algorithm (Least-Squares Policy Iteration) 7 Discussion Error at each iteration (LSTD error) Final performance bound of LSPI
3 Sequential Decision-Making under Uncertainty? How Can I...? Move around in the physical world (e.g. driving, navigation) Play and win a game Retrieve information over the web Medical diagnosis and treatment Maximize the throughput of a factory Optimize the performance of a rescue team
4 Reinforcement Learning (RL) RL: A class of learning problems in which an agent interacts with a dynamic, stochastic, and incompletely known environment Goal: Learn an action-selection strategy, or policy, to optimize some measure of its long-term performance Interaction: Modeled as a MDP or a POMDP
5 Markov Decision Process MDP An MDP M is a tuple X,A, r, p,γ. The state space X is a bounded closed subset of R d. The set of actions A is finite ( A < ). The reward function r : X A R is bounded by R max. The transition model p( x, a) is a distribution over X. γ (0, 1) is a discount factor. Policy: a mapping from states to actions π(x) A
6 Value Function For a policy π Value function V π : X R [ V π (x) = E γ t r ( X t,π(x t ) ) ] X 0 = x t=0 Action-value function Q π : X A R [ ] Q π (x, a) = E γ t r(x t, A t ) X 0 = x, A 0 = a t=0
7 Notation Bellman Operator Bellman operator for policy π T π : B V (X; V max ) B V (X; V max ) V π is the unique fixed-point of the Bellman operator (T π V)(x) = r ( x,π(x) ) +γ p ( dy x,π(x) ) V(y) The action-value function Q π is defined as Q π (x, a) = r(x, a)+γ p(dy x, a)v π (y) X X
8 Optimal Value Function and Optimal Policy Optimal value function V (x) = sup V π (x) π x X Optimal action-value function Q (x, a) = sup Q π (x, a) π x X, a A A policy π is optimal if V π (x) = V (x) x X
9 Notation Bellman Optimality Operator Bellman optimality operator T : B V (X; V max ) B V (X; V max ) V is the unique fixed-point of the Bellman optimality operator [ ] (T V)(x) = max r(x, a)+γ p(dy x, a)v(y) a A X Optimal action-value function Q is defined as Q (x, a) = r(x, a)+γ p(dy x, a)v (y) X
10 Properties of Bellman Operators Monotonicity: if V 1 V 2 component-wise T π V 1 T π V 2 and T V 1 T V 2 Max-Norm Contraction: V 1, V 2 B V (X; V max ) T π V 1 T π V 2 γ V 1 V 2 T V 1 T V 2 γ V 1 V 2
11 Dynamic Programming Algorithms Value Iteration start with an arbitrary action-value function Q 0 at each iteration k Q k+1 = T Q k Convergence lim k V k = V. V V k+1 = T V T V k γ V V k γ k+1 V V 0 k 0
12 Dynamic Programming Algorithms Policy Iteration start with an arbitrary policy π 0 at each iteration k Convergence Policy Evaluation: Compute Q π k Policy Improvement: Compute the greedy policy w.r.t. Q π k π k+1 (x) = (Gπ k )(x) = arg max Q π k (x, a) a A PI generates a sequence of policies with increasing performance (V π k+1 V π k ) and stops after a finite number of iterations with the optimal policy π. V π k = T π k V π k T V π k = T π k+1 V π k lim n (T π k+1 ) n V π k = V π k+1
13 Approximate Dynamic Programming
14 Approximate Dynamic Programming Algorithms Value Iteration start with an arbitrary action-value function Q 0 at each iteration k Q k+1 = T Q k What if Q k+1 T Q k? Q Q k+1? γ Q Q k
15 Approximate Dynamic Programming Algorithms Policy Iteration start with an arbitrary policy π 0 at each iteration k Policy Evaluation: Compute Q π k Policy Improvement: Compute the greedy policy w.r.t. Q π k π k+1 (x) = (Gπ k )(x) = arg max Q π k (x, a) a A What if we cannot compute Q π k exactly? (Compute Qπ k Q π k instead) π k+1 (x) = arg max a A Q π k (x, a) (Gπ k )(x) V π k+1? V π k
16 Statistical Learning Theory in RL & ADP Approximate Value Iteration (AVI) Q k+1 T Q k finding a function that best approximatestq k Q = min f f TQ k µ only noisy observations of T Q k are available T Qk Target Function = T Q k Noisy Observation = T Q k we minimize the empirical error Q k+1 = Q = min f f T Q k µ with the target of minimizing the true error Q = min f f TQ k µ Objective: Q TQ k µ Q Q µ + Q TQ k µ }{{}}{{} estimation error approximation error to be small regression
17 Statistical Learning Theory in RL & ADP Approximate Value Iteration (AVI) Q k+1 T Q k finding a function that best approximatestq k Q = min f f TQ k µ only noisy observations of T Q k are available T Qk Target Function = T Q k Noisy Observation = T Q k we minimize the empirical error Q k+1 = Q = min f f T Q k µ with the target of minimizing the true error Q = min f f TQ k µ Objective: Q TQ k µ Q Q µ + Q TQ k µ }{{}}{{} estimation error approximation error to be small regression
18 Statistical Learning Theory in RL & ADP Approximate Value Iteration (AVI) Q k+1 T Q k finding a function that best approximatestq k Q = min f f TQ k µ only noisy observations of T Q k are available T Qk Target Function = T Q k Noisy Observation = T Q k we minimize the empirical error Q k+1 = Q = min f f T Q k µ with the target of minimizing the true error Q = min f f TQ k µ Objective: Q TQ k µ Q Q µ + Q TQ k µ }{{}}{{} estimation error approximation error to be small regression
19 Statistical Learning Theory in RL & ADP Approximate Value Iteration (AVI) Q k+1 T Q k finding a function that best approximatestq k Q = min f f TQ k µ only noisy observations of T Q k are available T Qk Target Function = T Q k Noisy Observation = T Q k we minimize the empirical error Q k+1 = Q = min f f T Q k µ with the target of minimizing the true error Q = min f f TQ k µ Objective: Q TQ k µ Q Q µ + Q TQ k µ }{{}}{{} estimation error approximation error to be small regression
20 Statistical Learning Theory in RL & ADP Approximate Value Iteration (AVI) Q k+1 T Q k finding a function that best approximatestq k Q = min f f TQ k µ only noisy observations of T Q k are available T Qk Target Function = T Q k Noisy Observation = T Q k we minimize the empirical error Q k+1 = Q = min f f T Q k µ with the target of minimizing the true error Q = min f f TQ k µ Objective: Q TQ k µ Q Q µ + Q TQ k µ }{{}}{{} estimation error approximation error to be small regression
21 Statistical Learning Theory in RL & ADP Approximate Value Iteration (AVI) Q k+1 T Q k finding a function that best approximatestq k Q = min f f TQ k µ only noisy observations of T Q k are available T Qk Target Function = T Q k Noisy Observation = T Q k we minimize the empirical error Q k+1 = Q = min f f T Q k µ with the target of minimizing the true error Q = min f f TQ k µ Objective: Q TQ k µ Q Q µ + Q TQ k µ }{{}}{{} estimation error approximation error to be small regression
22 Statistical Learning Theory in RL & ADP Approximate Policy Iteration (API) - policy evaluation finding a function that best approximates Q π k Q = min f f Q π k µ only noisy observations of Q π k are available Qπ k Target Function= Q π k Noisy Observation = Q π k we minimize the empirical error Q = minf f Q π k µ with the target of minimizing the true error Q = min f f Q π k µ Objective: Q Q π k µ Q Q µ + Q Q π k µ }{{}}{{} estimation error approximation error to be small regression
23 Statistical Learning Theory in RL & ADP Approximate Policy Iteration (API) π k+1 Gπ k finding a policy that best approximatesgπ k π = min f L(f,π k ;µ) we minimize the empirical error π k+1 = π = min f L(f,πk ; µ) with the target of minimizing the true error π = min f L(f,π k ;µ) Objective: L( π,π k ;µ) L( π,π;µ) + L(π,π k ;µ) }{{}}{{} estimation error approximation error to be small classification (we do not discuss it in this talk)
24 Statistical Learning Theory in RL & ADP Approximate Policy Iteration (API) - policy evaluation finding the fixed-point of T π k only noisy observations of T π k are available T π k a fixed-point problem
25 SLT in RL & ADP supervised learning methods (regression, classification) appear in the inner-loop of ADP algorithms (performance at each iteration) tools from SLT that are used to analyze supervised learning methods can be used in RL and ADP (e.g., how many samples are required to achieve a certain performance) What makes RL more challenging? the objective is not always to recover a target function from its noisy observations (fixed-point vs. regression) the target sometimes has to be approximated given sample trajectories (non i.i.d. samples) propagation of error (control problem) is there any hope?
26 Approximate Value Iteration (AVI) V k+1 = T V k +ǫ k or V k+1 T V k = ǫ k Proposition (AVI Error Propagation) We run AVI for K iterations and π K = GV K Proof V V π K 2γ (1 γ) 2 max ǫ k + 2γK+1 0 k<k 1 γ V V 0. V V k+1 T V T V k + T V k V k+1 = γ V V k +ǫ k so K 1 V V K γ K 1 k ǫ k +γ K V V γ max ǫ k +γ K V V 0 0 k<k k=0 the result follows by the fact that V V π K 2γ 1 γ V V K.
27 Approximate Policy Iteration (API) 1 V k = V π k +ǫk or V k V π k = ǫ k (Policy Evaluation Error) 2 V k = T π k Vk +ǫ k or V k T π k Vk = ǫ k (Bellman Residual) Proposition (API Asymptotic Performance) (1) lim sup V V π k k 2γ (1 γ) lim sup V 2 k V π k k }{{} ǫ k (2) lim sup V V π k k 2γ (1 γ) lim sup V 2 k T π k V k k }{{} ǫ k
28 Approximate Dynamic Programming (ADP) Proposition (AVI Asymptotic Performance) lim sup V V π k k 2γ (1 γ) lim sup V 2 k+1 T V k k }{{} ǫ k Proposition (API Asymptotic Performance) (1) lim sup V V π k k (2) lim sup V V π k k 2γ (1 γ) 2γ (1 γ) lim sup V 2 k V π k k }{{} ǫ k lim sup V 2 k T π k V k k }{{} ǫ k
29 Error Propagation
30 AVI Error Propagation Error at each iteration k: ǫ k = T V k V k+1 π K is a greedy policy w.r.t. V K 1 π K = G(V K 1 ) Proposition (AVI Pointwise Error Bound) V V π K (I γp π K ) 1{ K 1 γ K k[ (P π ) K k + P π K P π K 1...P ] π k+1 ǫ k k=0 +γ K+1[ (P π ) K+1 +(P π K P π K 1...P π 0 ) ] } V V 0
31 AVI Error Propagation Proposition (AVI L p Error Bound) ǫ k = T V k V k+1 V V π K p,ρ V V π K [ ] 2γ C 1/p (1 γ) 2 ρ,µ max ǫ k p,µ + 2γ K/p V max 0 k<k [ ] 2γ C 1/p (1 γ) 2 µ max ǫ k p,µ + 2γ K/p V max 0 k<k (A1) (A2)
32 AVI Error Propagation Proposition (AVI L p Error Bound) ǫ k = T V k V k+1 V V π K p,ρ V V π K [ ] 2γ C 1/p (1 γ) 2 ρ,µ max ǫ k p,µ + 2γ K/p V max 0 k<k [ ] 2γ C 1/p (1 γ) 2 µ max ǫ k p,µ + 2γ K/p V max 0 k<k (A1) (A2) ǫ k p,µ : error at each iteration k, note that ǫ k = T V k V k+1
33 AVI Error Propagation Proposition (AVI L p Error Bound) ǫ k = T V k V k+1 V V π K p,ρ V V π K [ ] 2γ C 1/p (1 γ) 2 ρ,µ max ǫ k p,µ + 2γ K/p V max 0 k<k [ ] 2γ C 1/p (1 γ) 2 µ max ǫ k p,µ + 2γ K/p V max 0 k<k (A1) (A2) ǫ k p,µ : error at each iteration k, note that ǫ k = T V k V k+1 2γ K/p V max : initialization error V V 0
34 AVI Error Propagation Proposition (AVI L p Error Bound) ǫ k = T V k V k+1 V V π K p,ρ V V π K [ ] 2γ C 1/p (1 γ) 2 ρ,µ max ǫ k p,µ + 2γ K/p V max 0 k<k [ ] 2γ C 1/p (1 γ) 2 µ max ǫ k p,µ + 2γ K/p V max 0 k<k (A1) (A2) ǫ k p,µ : error at each iteration k, note that ǫ k = T V k V k+1 2γ K/p V max : initialization error V V 0 C ρ,µ, C µ : final performance is evaluated w.r.t. a measure ρ µ
35 AVI Error Propagation (Concentrability Coefficients) Final performance is evaluated w.r.t. a measure ρ µ, V V π K p,ρ Assumption 1. (Uniformly Stochastic Transitions) For all x X and a A, there exists a constant C µ < such that P( x, a) C µ µ( ). Assumption 2. (Discounted-Average Concentrability of Future-State Distribution) For any sequence of policies {π m } m 1, there exists a constant c ρ,µ (m) < such that ρp π 1 P π 2...P π m c ρ,µ (m)µ. We define C ρ,µ = (1 γ) 2 m 1 mγ m 1 c ρ,µ (m) Note that C ρ,µ C µ.
36 API Error Propagation Error at each iteration k: ǫ k = V k T π k V k π K is a greedy policy w.r.t. V K 1 π K = G(V K 1 ) Proposition (API Pointwise Error Bound) V V π K K 1 γ (γp π ) K k 1 E k ǫ k +(γp π ) K V V π 0 k=0 where E k = P π k+1 (I γp π k+1 ) 1 P π (I γp π k ) 1
37 API Error Propagation Proposition (API L p Error Bound) V V π K p,ρ [ ] 2γ C 1/p (1 γ) 2 ρ,µ max ǫ k p,µ + 2γ K/p V max 0 k<k ǫ k = V k T π k V k (A1) V V π K [ ] 2γ C 1/p (1 γ) 2 µ max ǫ k p,µ + 2γ K/p V max 0 k<k (A2)
38 API Error Propagation Proposition (API L p Error Bound) V V π K p,ρ [ ] 2γ C 1/p (1 γ) 2 ρ,µ max ǫ k p,µ + 2γ K/p V max 0 k<k ǫ k = V k T π k V k (A1) V V π K [ ] 2γ C 1/p (1 γ) 2 µ max ǫ k p,µ + 2γ K/p V max 0 k<k (A2) ǫ k p,µ : error at each iteration k, note that ǫ k = V k T π k Vk 2γ K/p V max : initialization error V V π 0 C ρ,µ, C µ : final performance is evaluated w.r.t. a measure ρ µ
39 API Error Propagation (Concentrability Coefficients) Final performance is evaluated w.r.t. a measure ρ µ, V V π K p,ρ Assumption 1. (Uniformly Stochastic Transitions) For all x X and a A, there exists a constant C µ < such that P( x, a) C µ µ( ). Assumption 2. (Discounted-Average Concentrability of Future-State Distribution) For any policy π and any non-negative integers s and t, there exists a constant c ρ,µ (s, t) < such that ρ(p ) s (P π ) t c ρ,µ (s, t)µ. We define C ρ,µ = (1 γ) 2 γ s+t c ρ,µ (s, t) s=0 t=0 Note that C ρ,µ C µ.
40 Finite-Sample Performance Bound of an AVI Algorithm
41 Approximate Value Iteration (AVI) if F is a function space, then V k+1 can be defined as V k+1 = inf V F V T V k? = Π? T V k (projection of T V k into F according to the norm L? ) if V k+1 = Π T V k then AVI converges to the unique fixed-point of Π T, i.e. V F : V = Π T V (T is a contraction in L -norm and Π is non-expansive) if we consider another norm, e.g. L 2 (µ), then AVI does not necessarily converge (Π 2,µ T is not necessarily a contraction)
42 An Approximate Value Iteration Algorithm Linear function space F = { f : f( ) = d j=1 α jϕ j ( ) } {ϕ j } d j=1 B ( (X,A); L ), φ : (X,A) R d, φ( ) = ( ϕ 1 ( ),...,ϕ d ( ) ) Fitted Q-Iteration (FQI) At each iteration k: Generate N samples of the form (X i, A i, X i, R i), where (X i, A i ) µ, X i p( X i, A i ), R i r(x i, A i ) { ((Xi Build the training set D k =, A i ), T Q k (X i, A i ) )} N, where i=1 T Q k (X i, A i ) = R i +γ max a A Q k (X i, a) Q k+1 = arg min f F f T Q k 2 N = arg min f F 1 N [ N i=1 f(xi, A i ) T Q k (X i, A i ) ] 2 (regression)
43 FQI - Error at Each Iteration Theorem (FQI - Error at Iteration k) Let F be a d-dim linear space, D k = { (X i, A i, X i, R i ) } N, i=1 (X i, A i ) iid µ, p( X i, A i ), R i = r(x i, A i ), and Q be the training set and the truncated X i solution at the k th iteration of FQI. Then with probability 1 δ, we have ( ) ( ) Q T Q k µ 4 inf f T Q k µ+o α log(1/δ) d log(n/δ) k +O. f F N N Note that Q k+1 = Q.
44 FQI - Error at Each Iteration Theorem (FQI - Error at Iteration k) Let F be a d-dim linear space, D k = { (X i, A i, X i, R i ) } N, i=1 (X i, A i ) iid µ, p( X i, A i ), R i = r(x i, A i ), and Q be the training set and the truncated X i solution at the k th iteration of FQI. Then with probability 1 δ, we have ( ) ( ) Q T Q k µ 4 inf f T Q k µ+o α log(1/δ) d log(n/δ) k +O. f F N N Note that Q k+1 = Q. N = # of samples, d = dimension of the linear function space F
45 FQI - Error at Each Iteration Theorem (FQI - Error at Iteration k) Let F be a d-dim linear space, D k = { (X i, A i, X i, R i ) } N, i=1 (X i, A i ) iid µ, p( X i, A i ), R i = r(x i, A i ), and Q be the training set and the truncated X i solution at the k th iteration of FQI. Then with probability 1 δ, we have ( ) ( ) Q T Q k µ 4 inf f T Q k µ+o α log(1/δ) d log(n/δ) k +O. f F N N Note that Q k+1 = Q. N = # of samples, d = dimension of the linear function space F α k f α k = Π 2,µ T Q k : the best approximation of T Q k in F w.r.t. µ
46 FQI - Error at Each Iteration FQI - Error at Iteration k ( ) ( ) log(1/δ) d log(n/δ) Q T Q k µ 4 inf f TQ k µ + O α k + O f F N N }{{}}{{} approximation error estimation error Approximation error: it depends on how well the function space F can approximatetq k Estimation error: it depends on the number of samples N, the dim of the function space d, and α k
47 FQI Error Bound Theorem (FQI Error Bound) Let Q 1 F be an arbitrary initial value function, Q 0,..., Q K 1 be the sequence of truncated action-value functions generated by FQI after K iterations, and π K be the greedy policy w.r.t. Q K 1. Then with probability 1 δ, we have V V π K ρ { ) 2γ log(k/δ) (1 γ) 2 C ρ,µ[ d µ(t F,F)+O (Q max N ν µ + O ( } d log(nk/δ) )]+2γ K/2 Q max N
48 FQI Error Bound Theorem (FQI Error Bound) Let Q 1 F be an arbitrary initial value function, Q 0,..., Q K 1 be the sequence of truncated action-value functions generated by FQI after K iterations, and π K be the greedy policy w.r.t. Q K 1. Then with probability 1 δ, we have V V π K ρ { ) 2γ log(k/δ) (1 γ) 2 C ρ,µ[ d µ(t F,F)+O (Q max N ν µ + O ( } d log(nk/δ) )]+2γ K/2 Q max N Approximation error: d µ(t F,F) = sup f F inf g F g Tf µ
49 FQI Error Bound Theorem (FQI Error Bound) Let Q 1 F be an arbitrary initial value function, Q 0,..., Q K 1 be the sequence of truncated action-value functions generated by FQI after K iterations, and π K be the greedy policy w.r.t. Q K 1. Then with probability 1 δ, we have { ) V V π 2γ log(k/δ) K ρ (1 γ) 2 C ρ,µ[ d µ(t F,F)+O (Q max N ν µ ( } d log(nk/δ) + O )]+2γ K/2 Q max N Approximation error: d µ(t F,F) = sup f F inf g F g Tf µ Estimation error: depends on N, d,ν µ, K. ν µ = the smallest eigenvalue of the Gram matrix ( ϕ i ϕ j dµ) i,j Note that α k Qmax ν µ
50 FQI Error Bound Theorem (FQI Error Bound) Let Q 1 F be an arbitrary initial value function, Q 0,..., Q K 1 be the sequence of truncated action-value functions generated by FQI after K iterations, and π K be the greedy policy w.r.t. Q K 1. Then with probability 1 δ, we have { ) V V π 2γ log(k/δ) K ρ (1 γ) 2 C ρ,µ[ d µ(t F,F)+O (Q max N ν µ ( } d log(nk/δ) + O )]+2γ K/2 Q max N Approximation error: d µ(t F,F) = sup f F inf g F g Tf µ Estimation error: depends on N, d,ν µ, K. ν µ = the smallest eigenvalue of the Gram matrix ( ϕ i ϕ j dµ) i,j Note that α k Qmax ν µ Initialization error: error due to the choice of the initial action-value function Q Q 0
51 Finite-Sample Performance Bound of an API Algorithm
52 Least-Squares Temporal-Difference Learning (LSTD) Linear function space F = { f : f( ) = d j=1 α jϕ j ( ) } {ϕ j } d j=1 B(X; L ), φ : X R d, φ( ) = ( ϕ 1 ( ),...,ϕ d ( ) ) V π is the fixed-point of T π V π may not belong to F T π V π = V π V π / F LSTD searches for the fixed-point of Π? T π instead (Π? is a projection into F w.r.t. L? -norm) Π T π is a contraction in L -norm L -projection is numerically expensive when the number of states is large or infinite LSTD searches for the fixed-point of Π 2,µ T π Π 2,µ g = arg min f F f g 2,µ
53 Least-Squares Temporal-Difference Learning (LSTD) When the fixed-point of Π µ T π exists, we call it the LSTD solution V TD = Π µ T π V TD T π V π T π V TD T π F Π µv π V TD = Π µ T π V TD r π,ϕ i µ }{{} b i T π V TD V TD,ϕ i µ = 0, i = 1,...,d r π +γp π V TD V TD,ϕ i µ = 0 d ϕ j γp π (j) ϕ j,ϕ i µ αtd }{{} = 0 i=1 A ij A α TD = b In general,π µt π is not a contraction and does not have a fixed-point. If µ = µ π, the stationary dist. of π, thenπ µ πt π has a unique fixed-point.
54 LSTD Algorithm Proposition (LSTD Performance) V π V TD µ π 1 inf 1 γ 2 V F Vπ V µ π LSTD Algorithm We observe a trajectory generated by following the policy π (X 0, R 0, X 1, R 1,...,X N ) where X t+1 P ( X t,π(x t ) ) and R t = r ( X t,π(x t ) ) We build estimators of the matrix A and vector b  ij = 1 N 1 ϕ i (X t ) [ ϕ j (X t ) γϕ j (X t+1 ) ], bi = 1 N 1 ϕ i (X t )R t N N t=0 t=0  α TD = b, VTD ( ) = φ( ) α TD when n then  A and b b, and thus, α TD α TD and V TD V TD.
55 LSTD Error Bound When the Markov chain induced by the policy under evaluation π has a stationary distribution µ π (Markov chain is ergodic - e.g.β-mixing), then Theorem (LSTD Error Bound) Let Ṽ be the truncated LSTD solution computed using n samples along a trajectory generated by following the policy π. Then with probability 1 δ, we have ( ) V π Ṽ µ π c d log(d/δ) inf 1 γ 2 f F Vπ f µ π + O n ν n = # of samples, d = dimension of the linear function space F ν = the smallest eigenvalue of the Gram matrix ( ϕ i ϕ j dµ π ) i,j (Assume: eigenvalues of the Gram matrix are strictly positive - existence of the model-based LSTD solution) β-mixing coefficients are hidden in O notation
56 LSTD Error Bound LSTD Error Bound V π Ṽ µ π c 1 γ 2 inf f F Vπ f µ π + O }{{} approximation error ( ) d log(d/δ) n ν } {{ } estimation error Approximation error: it depends on how well the function space F can approximate the value function V π Estimation error: it depends on the number of samples n, the dim of the function space d, the smallest eigenvalue of the Gram matrix ν, the mixing properties of the Markov chain (hidden in O)
57 LSPI Error Bound Theorem (LSPI Error Bound) Let V 1 F be an arbitrary initial value function, Ṽ0,...,ṼK 1 be the sequence of truncated value functions generated by LSPI after K iterations, and π K be the greedy policy w.r.t. ṼK 1. Then with probability 1 δ, we have V V π K ρ { ( )] } 4γ d log(dk/δ) (1 γ) 2 CC ρ,µ[ ce 0 (F)+O +γ K 1 2 R max n ν µ
58 LSPI Error Bound Theorem (LSPI Error Bound) Let V 1 F be an arbitrary initial value function, Ṽ0,...,ṼK 1 be the sequence of truncated value functions generated by LSPI after K iterations, and π K be the greedy policy w.r.t. ṼK 1. Then with probability 1 δ, we have V V π K ρ { ( )] } 4γ d log(dk/δ) (1 γ) 2 CC ρ,µ[ ce 0 (F)+O +γ K 1 2 R max n ν µ Approximation error: E 0 (F) = sup π G( F) inf f F V π f µ π
59 LSPI Error Bound Theorem (LSPI Error Bound) Let V 1 F be an arbitrary initial value function, Ṽ0,...,ṼK 1 be the sequence of truncated value functions generated by LSPI after K iterations, and π K be the greedy policy w.r.t. ṼK 1. Then with probability 1 δ, we have V V π K ρ { ( )] } 4γ d log(dk/δ) (1 γ) 2 CC ρ,µ[ ce 0 (F)+O +γ K 1 2 R max n ν µ Approximation error: E 0 (F) = sup π G( F) inf f F V π f µ π Estimation error: depends on n, d,ν µ, K
60 LSPI Error Bound Theorem (LSPI Error Bound) Let V 1 F be an arbitrary initial value function, Ṽ0,...,ṼK 1 be the sequence of truncated value functions generated by LSPI after K iterations, and π K be the greedy policy w.r.t. ṼK 1. Then with probability 1 δ, we have V V π K ρ { ( )] } 4γ d log(dk/δ) (1 γ) 2 CC ρ,µ[ ce 0 (F)+O +γ K 1 2 R max n ν µ Approximation error: E 0 (F) = sup π G( F) inf f F V π f µ π Estimation error: depends on n, d,ν µ, K Initialization error: error due to the choice of the initial value function or initial policy V V π 0
61 LSPI Error Bound LSPI Error Bound V V π K ρ { ( )] } 4γ d log(dk/δ) (1 γ) 2 CC ρ,µ[ ce 0 (F)+O +γ K 1 2 R max n ν µ Lower-Bounding Distribution There exists a distributionµ such that for any policy π G( F), we have µ Cµ π, where C < is a constant and µ π is the stationary distribution of π. Furthermore, we can define the concentrability coefficient C ρ,µ as before.
62 LSPI Error Bound LSPI Error Bound V V π K ρ { ( )] } 4γ d log(dk/δ) (1 γ) 2 CC ρ,µ[ ce 0 (F)+O +γ K 1 2 R max n ν µ Lower-Bounding Distribution There exists a distributionµ such that for any policy π G( F), we have µ Cµ π, where C < is a constant and µ π is the stationary distribution of π. Furthermore, we can define the concentrability coefficient C ρ,µ as before. ν µ = the smallest eigenvalue of the Gram matrix ( ϕ i ϕ j dµ) i,j
63 Discussion we obtain the optimal rate of regression and classification for RL (ADP) algorithms What makes RL more challenging then? the propagation of error (control problem) the approximation error is more complex the sampling problem (how to choose µ - exploration problem)
64 Other Finite-Sample Analysis Results in RL Approximate Value Iteration [MS08] Approximate Policy Iteration LSTD and LSPI [LGM10, LGM11] Bellman Residual Minimization [MMLG10] Modified Bellman Residual Minimization [ASM08] Classification-based Policy Iteration [FYG06, LGM10, GLGS11] Regularized Approximate Dynamic Programming L 2 -Regularization L 2 -Regularized Policy Iteration [FGSM08] L 2 -Regularized Fitted Q-Iteration [FGSM09] L 1 -Regularization and High-Dimensional RL Lasso-TD [GLMH11] LSTD (LSPI) with Random Projections [GLMM10]
65 Bibliography I Antos, A., Szepesvári, Cs., and Munos, R. Learning Near-Optimal Policies with Bellman Residual Minimization-based Fitted Policy Iteration and a Single Sample Path. Machine Learning Journal, 71:89 129, Farahmand, A., Ghavamzadeh, M., Szepesvári Cs., and Mannor, S. Regularized Policy Iteration. Proceedings of Advances in Neural Information Processing Systems 21, pp , Farahmand, A., Ghavamzadeh, M., Szepesvári Cs., and Mannor, S. Regularized Fitted Q-iteration for Planning in Continuous-Space Markovian Decision Problems. Proceedings of the American Control Conference, pp , Fern, A., Yoon, S., and Givan, R. Approximate Policy Iteration with a Policy Language Bias: Solving Relational Markov Decision Processes. Journal of Artificial Intelligence Research, 25:85 118, Gabillon, V., Lazaric, A., Ghavamzadeh, M., and Scherrer, B. Classification-based Policy Iteration with a Critic. Proceedings of the Twenty-Eighth International Conference on Machine Learning, pp , Ghavamzadeh, M., Lazaric A., Munos, R., and Hoffman, M. Finite-Sample Analysis of Lasso-TD. Proceedings of the Twenty-Eighth International Conference on Machine Learning, pp , Ghavamzadeh, M., Lazaric, A., Maillard, O., and Munos, R. LSTD with Random Projections. Proceedings of Advances in Neural Information Processing Systems 23, pp , 2010.
66 Bibliography II Lazaric A., Ghavamzadeh, M., and Munos, R. Analysis of a Classification-based Policy Iteration Algorithm. Proceedings of the Twenty-Seventh International Conference on Machine Learning, pp , Lazaric A., Ghavamzadeh, M., and Munos, R. Finite-Sample Analysis of LSTD. Proceedings of the Twenty-Seventh International Conference on Machine Learning, pp , Lazaric A., Ghavamzadeh, M., and Munos, R. Finite-Sample Analysis of Least-Squares Policy Iteration. Accepted at the Journal of Machine Learning Research, Maillard, O., Munos, R., Lazaric A., and Ghavamzadeh, M. Finite-Sample Analysis of Bellman Residual Minimization. Proceedings of the Second Asian Conference on Machine Learning, pp , Munos, R. and Szepesvári, Cs. Finite-Time Bounds for Fitted Value Iteration. Journal of Machine Learning Research, 9: , Munos, R. Performance Bounds in Lp-norm for Approximate Value Iteration. SIAM Journal of Control and Optimization, Munos, R. Error Bounds for Approximate Policy Iteration. Proceedings of the Nineteenth International Conference on Machine Learning, pp , 2003.
Approximate Dynamic Programming
Approximate Dynamic Programming A. LAZARIC (SequeL Team @INRIA-Lille) ENS Cachan - Master 2 MVA SequeL INRIA Lille MVA-RL Course Approximate Dynamic Programming (a.k.a. Batch Reinforcement Learning) A.
More informationApproximate Dynamic Programming
Approximate Dynamic Programming A. LAZARIC (SequeL Team @INRIA-Lille) Ecole Centrale - Option DAD SequeL INRIA Lille EC-RL Course Value Iteration: the Idea 1. Let V 0 be any vector in R N A. LAZARIC Reinforcement
More informationAnalysis of Classification-based Policy Iteration Algorithms
Journal of Machine Learning Research 17 (2016) 1-30 Submitted 12/10; Revised 9/14; Published 4/16 Analysis of Classification-based Policy Iteration Algorithms Alessandro Lazaric 1 Mohammad Ghavamzadeh
More informationApproximate Dynamic Programming
Master MVA: Reinforcement Learning Lecture: 5 Approximate Dynamic Programming Lecturer: Alessandro Lazaric http://researchers.lille.inria.fr/ lazaric/webpage/teaching.html Objectives of the lecture 1.
More informationMarkov Decision Processes and Dynamic Programming
Markov Decision Processes and Dynamic Programming A. LAZARIC (SequeL Team @INRIA-Lille) Ecole Centrale - Option DAD SequeL INRIA Lille EC-RL Course In This Lecture A. LAZARIC Markov Decision Processes
More informationChapter 13 Wow! Least Squares Methods in Batch RL
Chapter 13 Wow! Least Squares Methods in Batch RL Objectives of this chapter: Introduce batch RL Tradeoffs: Least squares vs. gradient methods Evaluating policies: Fitted value iteration Bellman residual
More informationAnalysis of Classification-based Policy Iteration Algorithms. Abstract
Analysis of Classification-based Policy Iteration Algorithms Analysis of Classification-based Policy Iteration Algorithms Alessandro Lazaric Mohammad Ghavamzadeh Rémi Munos INRIA Lille - Nord Europe, Team
More informationMarkov Decision Processes and Dynamic Programming
Markov Decision Processes and Dynamic Programming A. LAZARIC (SequeL Team @INRIA-Lille) ENS Cachan - Master 2 MVA SequeL INRIA Lille MVA-RL Course How to model an RL problem The Markov Decision Process
More informationRegularized Least Squares Temporal Difference learning with nested l 2 and l 1 penalization
Regularized Least Squares Temporal Difference learning with nested l 2 and l 1 penalization Matthew W. Hoffman 1, Alessandro Lazaric 2, Mohammad Ghavamzadeh 2, and Rémi Munos 2 1 University of British
More informationClassification-based Policy Iteration with a Critic
Victor Gabillon Alessandro Lazaric Mohammad Ghavamzadeh IRIA Lille - ord Europe, Team SequeL, FRACE Bruno Scherrer IRIA ancy - Grand Est, Team Maia, FRACE Abstract In this paper, we study the effect of
More informationIntroduction to Reinforcement Learning
Introduction to Reinforcement Learning Rémi Munos SequeL project: Sequential Learning http://researchers.lille.inria.fr/ munos/ INRIA Lille - Nord Europe Machine Learning Summer School, September 2011,
More informationClassification-based Policy Iteration with a Critic
Victor Gabillon Alessandro Lazaric Mohammad Ghavamzadeh IRIA Lille - ord Europe, Team SequeL, FRACE Bruno Scherrer IRIA ancy - Grand Est, Team Maia, FRACE Abstract In this paper, we study the effect of
More informationarxiv: v1 [cs.lg] 6 Jun 2013
Policy Search: Any Local Optimum Enjoys a Global Performance Guarantee Bruno Scherrer, LORIA MAIA project-team, Nancy, France, bruno.scherrer@inria.fr Matthieu Geist, Supélec IMS-MaLIS Research Group,
More informationA Dantzig Selector Approach to Temporal Difference Learning
Matthieu Geist Supélec, IMS Research Group, Metz, France Bruno Scherrer INRIA, MAIA Project Team, Nancy, France Alessandro Lazaric and Mohammad Ghavamzadeh INRIA Lille - Team SequeL, France matthieu.geist@supelec.fr
More informationBasics of reinforcement learning
Basics of reinforcement learning Lucian Buşoniu TMLSS, 20 July 2018 Main idea of reinforcement learning (RL) Learn a sequential decision policy to optimize the cumulative performance of an unknown system
More informationGeneralized Classification-based Approximate Policy Iteration
JMLR: Workshop and Conference Proceedings vol (2012) 1 11 European Workshop on Reinforcement Learning Generalized Classification-based Approximate Policy Iteration Amir-massoud Farahmand and Doina Precup
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 informationChristopher Watkins and Peter Dayan. Noga Zaslavsky. The Hebrew University of Jerusalem Advanced Seminar in Deep Learning (67679) November 1, 2015
Q-Learning Christopher Watkins and Peter Dayan Noga Zaslavsky The Hebrew University of Jerusalem Advanced Seminar in Deep Learning (67679) November 1, 2015 Noga Zaslavsky Q-Learning (Watkins & Dayan, 1992)
More informationReinforcement Learning. Introduction
Reinforcement Learning Introduction Reinforcement Learning Agent interacts and learns from a stochastic environment Science of sequential decision making Many faces of reinforcement learning Optimal control
More informationReinforcement Learning
Reinforcement Learning March May, 2013 Schedule Update Introduction 03/13/2015 (10:15-12:15) Sala conferenze MDPs 03/18/2015 (10:15-12:15) Sala conferenze Solving MDPs 03/20/2015 (10:15-12:15) Aula Alpha
More informationFitted Q-iteration in continuous action-space MDPs
Fitted Q-iteration in continuous action-space MDPs András Antos Computer and Automation Research Inst of the Hungarian Academy of Sciences Kende u 13-17, Budapest 1111, Hungary antos@sztakihu Rémi Munos
More informationReinforcement Learning as Classification Leveraging Modern Classifiers
Reinforcement Learning as Classification Leveraging Modern Classifiers Michail G. Lagoudakis and Ronald Parr Department of Computer Science Duke University Durham, NC 27708 Machine Learning Reductions
More informationMarkov Decision Processes Infinite Horizon Problems
Markov Decision Processes Infinite Horizon Problems Alan Fern * * Based in part on slides by Craig Boutilier and Daniel Weld 1 What is a solution to an MDP? MDP Planning Problem: Input: an MDP (S,A,R,T)
More informationMDP Preliminaries. Nan Jiang. February 10, 2019
MDP Preliminaries Nan Jiang February 10, 2019 1 Markov Decision Processes In reinforcement learning, the interactions between the agent and the environment are often described by a Markov Decision Process
More informationAnalysis of a Classification-based Policy Iteration Algorithm
Alessandro Lazaric alessandro.lazaric@inria.fr Mohammad Ghavamzadeh mohammad.ghavamzadeh@inria.fr Rémi Munos remi.munos@inria.fr SequeL Project, IRIA Lille-ord Europe, 40 avenue Halley, 59650 Villeneuve
More informationThe Art of Sequential Optimization via Simulations
The Art of Sequential Optimization via Simulations Stochastic Systems and Learning Laboratory EE, CS* & ISE* Departments Viterbi School of Engineering University of Southern California (Based on joint
More informationIntroduction to Reinforcement Learning Part 1: Markov Decision Processes
Introduction to Reinforcement Learning Part 1: Markov Decision Processes Rowan McAllister Reinforcement Learning Reading Group 8 April 2015 Note I ve created these slides whilst following Algorithms for
More informationUnderstanding (Exact) Dynamic Programming through Bellman Operators
Understanding (Exact) Dynamic Programming through Bellman Operators Ashwin Rao ICME, Stanford University January 15, 2019 Ashwin Rao (Stanford) Bellman Operators January 15, 2019 1 / 11 Overview 1 Value
More informationInternet Monetization
Internet Monetization March May, 2013 Discrete time Finite A decision process (MDP) is reward process with decisions. It models an environment in which all states are and time is divided into stages. Definition
More informationApproximate Dynamic Programming for Two-Player Zero-Sum Markov Games
Julien Perolat (1) Bruno Scherrer (2) Bilal Piot (1) Olivier Pietquin (1,3) (1) Univ. Lille, CRIStAL, SequeL team, France (2) Inria, Villers-lès-Nancy, F-46, France (3) Institut Universitaire de France
More informationLecture 18: Reinforcement Learning Sanjeev Arora Elad Hazan
COS 402 Machine Learning and Artificial Intelligence Fall 2016 Lecture 18: Reinforcement Learning Sanjeev Arora Elad Hazan Some slides borrowed from Peter Bodik and David Silver Course progress Learning
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 informationQ-Learning for Markov Decision Processes*
McGill University ECSE 506: Term Project Q-Learning for Markov Decision Processes* Authors: Khoa Phan khoa.phan@mail.mcgill.ca Sandeep Manjanna sandeep.manjanna@mail.mcgill.ca (*Based on: Convergence of
More informationLeast squares policy iteration (LSPI)
Least squares policy iteration (LSPI) Charles Elkan elkan@cs.ucsd.edu December 6, 2012 1 Policy evaluation and policy improvement Let π be a non-deterministic but stationary policy, so p(a s; π) is the
More informationRegularities in Sequential Decision-Making Problems. Amir massoud Farahmand
Regularities in Sequential Decision-Making Problems Amir massoud Farahmand 1 Contents 1 Introduction 5 1.1 Agent Design as a Sequential Decision Making Problem... 5 1.2 Regularities and Adaptive Algorithms.............
More informationZero-Sum Stochastic Games An algorithmic review
Zero-Sum Stochastic Games An algorithmic review Emmanuel Hyon LIP6/Paris Nanterre with N Yemele and L Perrotin Rosario November 2017 Final Meeting Dygame Dygame Project Amstic Outline 1 Introduction Static
More informationCentral-limit approach to risk-aware Markov decision processes
Central-limit approach to risk-aware Markov decision processes Jia Yuan Yu Concordia University November 27, 2015 Joint work with Pengqian Yu and Huan Xu. Inventory Management 1 1 Look at current inventory
More informationMS&E338 Reinforcement Learning Lecture 1 - April 2, Introduction
MS&E338 Reinforcement Learning Lecture 1 - April 2, 2018 Introduction Lecturer: Ben Van Roy Scribe: Gabriel Maher 1 Reinforcement Learning Introduction In reinforcement learning (RL) we consider an agent
More informationLecture notes for Analysis of Algorithms : Markov decision processes
Lecture notes for Analysis of Algorithms : Markov decision processes Lecturer: Thomas Dueholm Hansen June 6, 013 Abstract We give an introduction to infinite-horizon Markov decision processes (MDPs) with
More informationCS599 Lecture 1 Introduction To RL
CS599 Lecture 1 Introduction To RL Reinforcement Learning Introduction Learning from rewards Policies Value Functions Rewards Models of the Environment Exploitation vs. Exploration Dynamic Programming
More informationINTRODUCTION TO MARKOV DECISION PROCESSES
INTRODUCTION TO MARKOV DECISION PROCESSES Balázs Csanád Csáji Research Fellow, The University of Melbourne Signals & Systems Colloquium, 29 April 2010 Department of Electrical and Electronic Engineering,
More informationPrioritized Sweeping Converges to the Optimal Value Function
Technical Report DCS-TR-631 Prioritized Sweeping Converges to the Optimal Value Function Lihong Li and Michael L. Littman {lihong,mlittman}@cs.rutgers.edu RL 3 Laboratory Department of Computer Science
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 informationLecture 3: Markov Decision Processes
Lecture 3: Markov Decision Processes Joseph Modayil 1 Markov Processes 2 Markov Reward Processes 3 Markov Decision Processes 4 Extensions to MDPs Markov Processes Introduction Introduction to MDPs Markov
More informationBalancing and Control of a Freely-Swinging Pendulum Using a Model-Free Reinforcement Learning Algorithm
Balancing and Control of a Freely-Swinging Pendulum Using a Model-Free Reinforcement Learning Algorithm Michail G. Lagoudakis Department of Computer Science Duke University Durham, NC 2778 mgl@cs.duke.edu
More informationProcedia Computer Science 00 (2011) 000 6
Procedia Computer Science (211) 6 Procedia Computer Science Complex Adaptive Systems, Volume 1 Cihan H. Dagli, Editor in Chief Conference Organized by Missouri University of Science and Technology 211-
More informationThe convergence limit of the temporal difference learning
The convergence limit of the temporal difference learning Ryosuke Nomura the University of Tokyo September 3, 2013 1 Outline Reinforcement Learning Convergence limit Construction of the feature vector
More informationMarkov decision processes
CS 2740 Knowledge representation Lecture 24 Markov decision processes Milos Hauskrecht milos@cs.pitt.edu 5329 Sennott Square Administrative announcements Final exam: Monday, December 8, 2008 In-class Only
More informationLeast-Squares λ Policy Iteration: Bias-Variance Trade-off in Control Problems
: Bias-Variance Trade-off in Control Problems Christophe Thiery Bruno Scherrer LORIA - INRIA Lorraine - Campus Scientifique - BP 239 5456 Vandœuvre-lès-Nancy CEDEX - FRANCE thierych@loria.fr scherrer@loria.fr
More informationReinforcement Learning
1 Reinforcement Learning Chris Watkins Department of Computer Science Royal Holloway, University of London July 27, 2015 2 Plan 1 Why reinforcement learning? Where does this theory come from? Markov decision
More informationArtificial Intelligence & Sequential Decision Problems
Artificial Intelligence & Sequential Decision Problems (CIV6540 - Machine Learning for Civil Engineers) Professor: James-A. Goulet Département des génies civil, géologique et des mines Chapter 15 Goulet
More informationLecture 4: Approximate dynamic programming
IEOR 800: Reinforcement learning By Shipra Agrawal Lecture 4: Approximate dynamic programming Deep Q Networks discussed in the last lecture are an instance of approximate dynamic programming. These are
More informationThe Fixed Points of Off-Policy TD
The Fixed Points of Off-Policy TD J. Zico Kolter Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology Cambridge, MA 2139 kolter@csail.mit.edu Abstract Off-policy
More informationilstd: Eligibility Traces and Convergence Analysis
ilstd: Eligibility Traces and Convergence Analysis Alborz Geramifard Michael Bowling Martin Zinkevich Richard S. Sutton Department of Computing Science University of Alberta Edmonton, Alberta {alborz,bowling,maz,sutton}@cs.ualberta.ca
More informationAn online kernel-based clustering approach for value function approximation
An online kernel-based clustering approach for value function approximation N. Tziortziotis and K. Blekas Department of Computer Science, University of Ioannina P.O.Box 1186, Ioannina 45110 - Greece {ntziorzi,kblekas}@cs.uoi.gr
More informationSpeedy Q-Learning. Abstract
Speedy Q-Learning Mohammad Gheshlaghi Azar Radboud University Nijmegen Geert Grooteplein N, 6 EZ Nijmegen, Netherlands m.azar@science.ru.nl Mohammad Ghavamzadeh INRIA Lille, SequeL Project 40 avenue Halley
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 information2534 Lecture 4: Sequential Decisions and Markov Decision Processes
2534 Lecture 4: Sequential Decisions and Markov Decision Processes Briefly: preference elicitation (last week s readings) Utility Elicitation as a Classification Problem. Chajewska, U., L. Getoor, J. Norman,Y.
More informationSome AI Planning Problems
Course Logistics CS533: Intelligent Agents and Decision Making M, W, F: 1:00 1:50 Instructor: Alan Fern (KEC2071) Office hours: by appointment (see me after class or send email) Emailing me: include CS533
More informationApproximate Dynamic Programming By Minimizing Distributionally Robust Bounds
Approximate Dynamic Programming By Minimizing Distributionally Robust Bounds Marek Petrik IBM T.J. Watson Research Center, Yorktown, NY, USA Abstract Approximate dynamic programming is a popular method
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 informationWeighted Sup-Norm Contractions in Dynamic Programming: A Review and Some New Applications
May 2012 Report LIDS - 2884 Weighted Sup-Norm Contractions in Dynamic Programming: A Review and Some New Applications Dimitri P. Bertsekas Abstract We consider a class of generalized dynamic programming
More informationAbstract Dynamic Programming
Abstract Dynamic Programming Dimitri P. Bertsekas Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology Overview of the Research Monograph Abstract Dynamic Programming"
More informationCourse 16:198:520: Introduction To Artificial Intelligence Lecture 13. Decision Making. Abdeslam Boularias. Wednesday, December 7, 2016
Course 16:198:520: Introduction To Artificial Intelligence Lecture 13 Decision Making Abdeslam Boularias Wednesday, December 7, 2016 1 / 45 Overview We consider probabilistic temporal models where the
More informationBandit models: a tutorial
Gdt COS, December 3rd, 2015 Multi-Armed Bandit model: general setting K arms: for a {1,..., K}, (X a,t ) t N is a stochastic process. (unknown distributions) Bandit game: a each round t, an agent chooses
More informationSequential decision making under uncertainty. Department of Computer Science, Czech Technical University in Prague
Sequential decision making under uncertainty Jiří Kléma Department of Computer Science, Czech Technical University in Prague https://cw.fel.cvut.cz/wiki/courses/b4b36zui/prednasky pagenda Previous lecture:
More informationAn Adaptive Clustering Method for Model-free Reinforcement Learning
An Adaptive Clustering Method for Model-free Reinforcement Learning Andreas Matt and Georg Regensburger Institute of Mathematics University of Innsbruck, Austria {andreas.matt, georg.regensburger}@uibk.ac.at
More informationRegularization and Feature Selection in. the Least-Squares Temporal Difference
Regularization and Feature Selection in Least-Squares Temporal Difference Learning J. Zico Kolter kolter@cs.stanford.edu Andrew Y. Ng ang@cs.stanford.edu Computer Science Department, Stanford University,
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 informationComputational complexity estimates for value and policy iteration algorithms for total-cost and average-cost Markov decision processes
Computational complexity estimates for value and policy iteration algorithms for total-cost and average-cost Markov decision processes Jefferson Huang Dept. Applied Mathematics and Statistics Stony Brook
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 informationOn the Complexity of Best Arm Identification with Fixed Confidence
On the Complexity of Best Arm Identification with Fixed Confidence Discrete Optimization with Noise Aurélien Garivier, Emilie Kaufmann COLT, June 23 th 2016, New York Institut de Mathématiques de Toulouse
More informationRegularization and Feature Selection in. the Least-Squares Temporal Difference
Regularization and Feature Selection in Least-Squares Temporal Difference Learning J. Zico Kolter kolter@cs.stanford.edu Andrew Y. Ng ang@cs.stanford.edu Computer Science Department, Stanford University,
More informationMarkov Decision Processes Chapter 17. Mausam
Markov Decision Processes Chapter 17 Mausam Planning Agent Static vs. Dynamic Fully vs. Partially Observable Environment What action next? Deterministic vs. Stochastic Perfect vs. Noisy Instantaneous vs.
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 informationMarks. bonus points. } Assignment 1: Should be out this weekend. } Mid-term: Before the last lecture. } Mid-term deferred exam:
Marks } Assignment 1: Should be out this weekend } All are marked, I m trying to tally them and perhaps add bonus points } Mid-term: Before the last lecture } Mid-term deferred exam: } This Saturday, 9am-10.30am,
More informationState Space Abstractions for Reinforcement Learning
State Space Abstractions for Reinforcement Learning Rowan McAllister and Thang Bui MLG RCC 6 November 24 / 24 Outline Introduction Markov Decision Process Reinforcement Learning State Abstraction 2 Abstraction
More informationActive Policy Iteration: Efficient Exploration through Active Learning for Value Function Approximation in Reinforcement Learning
Active Policy Iteration: fficient xploration through Active Learning for Value Function Approximation in Reinforcement Learning Takayuki Akiyama, Hirotaka Hachiya, and Masashi Sugiyama Department of Computer
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 informationDistributed Optimization. Song Chong EE, KAIST
Distributed Optimization Song Chong EE, KAIST songchong@kaist.edu Dynamic Programming for Path Planning A path-planning problem consists of a weighted directed graph with a set of n nodes N, directed links
More informationMarkov Decision Processes and Dynamic Programming
Master MVA: Reinforcement Learning Lecture: 2 Markov Decision Processes and Dnamic Programming Lecturer: Alessandro Lazaric http://researchers.lille.inria.fr/ lazaric/webpage/teaching.html Objectives of
More informationMulti-armed bandit models: a tutorial
Multi-armed bandit models: a tutorial CERMICS seminar, March 30th, 2016 Multi-Armed Bandit model: general setting K arms: for a {1,..., K}, (X a,t ) t N is a stochastic process. (unknown distributions)
More informationA Convergent O(n) Algorithm for Off-policy Temporal-difference Learning with Linear Function Approximation
A Convergent O(n) Algorithm for Off-policy Temporal-difference Learning with Linear Function Approximation Richard S. Sutton, Csaba Szepesvári, Hamid Reza Maei Reinforcement Learning and Artificial Intelligence
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 informationIs the Bellman residual a bad proxy?
Is the Bellman residual a bad proxy? Matthieu Geist 1, Bilal Piot 2,3 and Olivier Pietquin 2,3 1 Université de Lorraine & CNRS, LIEC, UMR 7360, Metz, F-57070 France 2 Univ. Lille, CNRS, Centrale Lille,
More informationReinforcement Learning and Control
CS9 Lecture notes Andrew Ng Part XIII Reinforcement Learning and Control We now begin our study of reinforcement learning and adaptive control. In supervised learning, we saw algorithms that tried to make
More informationDirect Policy Iteration with Demonstrations
Proceedings of the Twenty-Fourth International Joint onference on rtificial Intelligence (IJI 25) Direct Policy Iteration with Demonstrations Jessica hemali Machine Learning Department arnegie Mellon University
More informationCOMP3702/7702 Artificial Intelligence Lecture 11: Introduction to Machine Learning and Reinforcement Learning. Hanna Kurniawati
COMP3702/7702 Artificial Intelligence Lecture 11: Introduction to Machine Learning and Reinforcement Learning Hanna Kurniawati Today } What is machine learning? } Where is it used? } Types of machine learning
More informationMarkov Decision Processes Chapter 17. Mausam
Markov Decision Processes Chapter 17 Mausam Planning Agent Static vs. Dynamic Fully vs. Partially Observable Environment What action next? Deterministic vs. Stochastic Perfect vs. Noisy Instantaneous vs.
More informationPlanning in Markov Decision Processes
Carnegie Mellon School of Computer Science Deep Reinforcement Learning and Control Planning in Markov Decision Processes Lecture 3, CMU 10703 Katerina Fragkiadaki Markov Decision Process (MDP) A Markov
More informationLearning near-optimal policies with Bellman-residual minimization based fitted policy iteration and a single sample path
Machine Learning manuscript No. will be inserted by the editor Learning near-optimal policies with Bellman-residual minimization based fitted policy iteration and a single sample path András Antos 1, Csaba
More informationLow-rank Feature Selection for Reinforcement Learning
Low-rank Feature Selection for Reinforcement Learning Bahram Behzadian and Marek Petrik Department of Computer Science University of New Hampshire {bahram, mpetrik}@cs.unh.edu Abstract Linear value function
More informationLeast-Squares Methods for Policy Iteration
Least-Squares Methods for Policy Iteration Lucian Buşoniu, Alessandro Lazaric, Mohammad Ghavamzadeh, Rémi Munos, Robert Babuška, and Bart De Schutter Abstract Approximate reinforcement learning deals with
More informationValue and Policy Iteration
Chapter 7 Value and Policy Iteration 1 For infinite horizon problems, we need to replace our basic computational tool, the DP algorithm, which we used to compute the optimal cost and policy for finite
More informationGrundlagen der Künstlichen Intelligenz
Grundlagen der Künstlichen Intelligenz Formal models of interaction Daniel Hennes 27.11.2017 (WS 2017/18) University Stuttgart - IPVS - Machine Learning & Robotics 1 Today Taxonomy of domains Models of
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 Ron Parr CompSci 7 Department of Computer Science Duke University With thanks to Kris Hauser for some content RL Highlights Everybody likes to learn from experience Use ML techniques
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 informationECE276B: Planning & Learning in Robotics Lecture 16: Model-free Control
ECE276B: Planning & Learning in Robotics Lecture 16: Model-free Control Lecturer: Nikolay Atanasov: natanasov@ucsd.edu Teaching Assistants: Tianyu Wang: tiw161@eng.ucsd.edu Yongxi Lu: yol070@eng.ucsd.edu
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 information