Variance Reduction for Policy Gradient Methods. March 13, 2017

Size: px
Start display at page:

Download "Variance Reduction for Policy Gradient Methods. March 13, 2017"

Transcription

1 Variance Reduction for Policy Gradient Methods March 13, 2017

2 Reward Shaping

3 Reward Shaping

4 Reward Shaping Reward shaping: r(s, a, s ) = r(s, a, s ) + γφ(s ) Φ(s) for arbitrary potential Φ Theorem: r admits the same optimal policies as r. 1 Proof sketch: suppose Q satisfies Bellman equation (T Q = Q). If we transform r r, 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

5 Reward Shaping Theorem: R 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 [ r 0 + γr 1 + γ 2 r ] condition on either s 0 or (s 0, a 0 ) = E [ r 0 + γ r 1 + γ 2 r ] = 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)

6 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 ) ]

7 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 ) r t = E θ log π θ (a t s t )(r t + γv π (s t+1 ) V π (s t )) t [ ] = E log π θ (a t s t )A π (s t, a t ) t t Compromise: use more aggressive discount γλ, with λ (0, 1): called generalized advantage estimation [ ] E θ log π θ (a t s t ) (γλ) k r t+k t k=0

8 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

9 [Aside] Reward Shaping: Very Important 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

10 Variance Reduction for Policy Gradients

11 Variance Reduction We have the following policy gradient formula: [ T 1 ] θ E τ [R] = E τ θ log π(a t s t, θ)a π (s t, a t ) t=0 A π is not known, but we can plug in Ât, an advantage estimator Previously, we showed that taking  t = r t + r t+1 + r t+2 + b(s t ) for any function b(s t ), gives an unbiased policy gradient estimator. b(s t ) V π (s t ) gives variance reduction.

12 The Delayed Reward Problem With policy gradient methods, we are confounding the effect of multiple actions: mixes effect of a t, a t+1, a t+2,... Â t = r t + r t+1 + r t+2 + b(s t ) SNR of Ât scales roughly as 1/T Only at contributes to signal A π (s t, a t ), but a t+1, a t+2,... contribute to noise.

13 Variance Reduction with Discounts Discount factor γ, 0 < γ < 1, downweights the effect of rewards that are far in the future ignore long term dependencies We can form an advantage estimator using the discounted return:  γ t = r t + γr t+1 + γ 2 r t b(s }{{} t ) discounted return reduces to our previous estimator when γ = 1. So advantage has expectation zero, we should fit baseline to be discounted value function V π,γ (s) = E τ [ r0 + γr 1 + γ 2 r s 0 = s ] Discount γ is similar to using a horizon of 1/(1 γ) timesteps  γ t is a biased estimator of the advantage function

14 Value Functions in the Future Baseline accounts for and removes the effect of past actions Can also use the value function to estimate future rewards r t + γv (s t+1 ) cut off at one timestep r t + γr t+1 + γ 2 V (s t+2 ) cut off at two timesteps... r t + γr t+1 + γ 2 r t timesteps (no V )

15 Value Functions in the Future Subtracting out baselines, we get advantage estimators  (1) t = r t + γv (s t+1 ) V (s t )  (2) t = r t + r t+1 + γ 2 V (s t+2 ) V (s t )...  ( ) t = r t + γr t+1 + γ 2 r t V (s t )  (1) t has low variance but high bias,  ( ) t has high variance but low bias. Using intermediate k (say, 20) gives an intermediate amount of bias and variance

16 Finite-Horizon Methods: Advantage Actor-Critic A2C / A3C uses this fixed-horizon advantage estimator 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 (s t )  t = ˆR t V (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 (s) ˆR ] t ) 2 g is plugged into a stochastic gradient descent variant, 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)

17 A3C Video

18 A3C Results Score Beamrider DQN 1-step Q 1-step SARSA n-step Q A3C Training time (hours) Score Breakout DQN 1-step Q 1-step SARSA n-step Q A3C Training time (hours) Score Pong Score DQN 1-step Q 1-step SARSA n-step Q A3C Training time (hours) Q*bert DQN 1-step Q 1-step SARSA n-step Q A3C Score Training time (hours) Space Invaders DQN 1-step Q 1-step SARSA n-step Q A3C Training time (hours)

19 Reward Shaping

20 TD(λ) Methods: Generalized Advantage Estimation Recall, finite-horizon advantage estimators  (k) t = r t + γr t γ k 1 r t+k 1 + γ k V (s t+k ) V (s t ) Define the TD error δ t = r t + γv (s t+1 ) V (s t ) By a telescoping sum,  (k) t = δ t + γδ t γ k 1 δ t+k 1 Take exponentially weighted average of finite-horizon estimators: We obtain  λ = Â(1) t + λâ(2) t + λ 2  (3) t +...  λ t = δ t + (γλ)δ t+1 + (γλ) 2 δ t This scheme named generalized advantage estimation (GAE) in [1], though versions have appeared earlier, e.g., [2]. Related to TD(λ) J. Schulman, P. Moritz, S. Levine, M. Jordan, and P. Abbeel. High-dimensional continuous control using generalized advantage estimation. (2015) H. Kimura and S. Kobayashi. An Analysis of Actor/Critic Algorithms Using Eligibility Traces: Reinforcement Learning with Imperfect Value

21 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

22 TRPO+GAE Video

Policy Gradient Methods. February 13, 2017

Policy 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 information

Deep Reinforcement Learning via Policy Optimization

Deep Reinforcement Learning via Policy Optimization Deep Reinforcement Learning via Policy Optimization John Schulman July 3, 2017 Introduction Deep Reinforcement Learning: What to Learn? Policies (select next action) Deep Reinforcement Learning: What to

More information

Generalized Advantage Estimation for Policy Gradients

Generalized 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 information

arxiv: v5 [cs.lg] 9 Sep 2016

arxiv: 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 information

Reinforcement Learning via Policy Optimization

Reinforcement 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 information

REINFORCEMENT LEARNING

REINFORCEMENT 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 information

Lecture 9: Policy Gradient II 1

Lecture 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 information

Deep Reinforcement Learning

Deep 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 information

Deep Reinforcement Learning: Policy Gradients and Q-Learning

Deep 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 information

Lecture 9: Policy Gradient II (Post lecture) 2

Lecture 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 information

Reinforcement Learning and NLP

Reinforcement 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 information

Trust Region Policy Optimization

Trust 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 information

Lecture 8: Policy Gradient

Lecture 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 information

Reinforcement Learning for NLP

Reinforcement 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 information

Lecture 8: Policy Gradient I 2

Lecture 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 information

Deep reinforcement learning. Dialogue Systems Group, Cambridge University Engineering Department

Deep 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 information

Reinforcement Learning

Reinforcement 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 information

Forward Actor-Critic for Nonlinear Function Approximation in Reinforcement Learning

Forward 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 information

15-889e 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 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 information

REINFORCE Framework for Stochastic Policy Optimization and its use in Deep Learning

REINFORCE 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 information

Q-Learning in Continuous State Action Spaces

Q-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 information

Multi-Batch Experience Replay for Fast Convergence of Continuous Action Control

Multi-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 information

Advanced Policy Gradient Methods: Natural Gradient, TRPO, and More. March 8, 2017

Advanced 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 information

Reinforcement Learning

Reinforcement 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 information

Markov Decision Processes and Solving Finite Problems. February 8, 2017

Markov 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 information

Reinforcement Learning

Reinforcement 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 information

Temporal Difference. Learning KENNETH TRAN. Principal Research Engineer, MSR AI

Temporal 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 information

Deep Reinforcement Learning SISL. Jeremy Morton (jmorton2) November 7, Stanford Intelligent Systems Laboratory

Deep 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 information

INF 5860 Machine learning for image classification. Lecture 14: Reinforcement learning May 9, 2018

INF 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 information

arxiv: v4 [cs.lg] 14 Oct 2018

arxiv: 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 information

Reinforcement Learning and Deep Reinforcement Learning

Reinforcement 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 information

Lecture 7: Value Function Approximation

Lecture 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 information

6 Basic Convergence Results for RL Algorithms

6 Basic Convergence Results for RL Algorithms Learning in Complex Systems Spring 2011 Lecture Notes Nahum Shimkin 6 Basic Convergence Results for RL Algorithms We establish here some asymptotic convergence results for the basic RL algorithms, by showing

More information

Grundlagen der Künstlichen Intelligenz

Grundlagen 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 information

Reinforcement Learning with Function Approximation. Joseph Christian G. Noel

Reinforcement 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 information

Introduction to Reinforcement Learning. CMPT 882 Mar. 18

Introduction 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 information

Counterfactual Multi-Agent Policy Gradients

Counterfactual Multi-Agent Policy Gradients Counterfactual Multi-Agent Policy Gradients Shimon Whiteson Dept. of Computer Science University of Oxford joint work with Jakob Foerster, Gregory Farquhar, Triantafyllos Afouras, and Nantas Nardelli July

More information

Decision Theory: Markov Decision Processes

Decision 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 information

CS230: Lecture 9 Deep Reinforcement Learning

CS230: 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 information

Proximal Policy Optimization Algorithms

Proximal 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 information

Lecture 23: Reinforcement Learning

Lecture 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 information

Behavior Policy Gradient Supplemental Material

Behavior 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 information

Reinforcement Learning. Spring 2018 Defining MDPs, Planning

Reinforcement 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 information

Using Gaussian Processes for Variance Reduction in Policy Gradient Algorithms *

Using 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

Reinforcement Learning II. George Konidaris

Reinforcement 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 information

Olivier Sigaud. September 21, 2012

Olivier Sigaud. September 21, 2012 Supervised and Reinforcement Learning Tools for Motor Learning Models Olivier Sigaud Université Pierre et Marie Curie - Paris 6 September 21, 2012 1 / 64 Introduction Who is speaking? 2 / 64 Introduction

More information

arxiv: v1 [cs.ai] 5 Nov 2017

arxiv: v1 [cs.ai] 5 Nov 2017 arxiv:1711.01569v1 [cs.ai] 5 Nov 2017 Markus Dumke Department of Statistics Ludwig-Maximilians-Universität München markus.dumke@campus.lmu.de Abstract Temporal-difference (TD) learning is an important

More information

Comparing Deep Reinforcement Learning and Evolutionary Methods in Continuous Control

Comparing 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 information

Deep Reinforcement Learning. Scratching the surface

Deep 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 information

Reinforcement learning

Reinforcement 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 information

Reinforcement Learning II. George Konidaris

Reinforcement 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 information

Reinforcement Learning

Reinforcement 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 information

Soft 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 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 information

(Deep) Reinforcement Learning

(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 information

Reinforcement Learning

Reinforcement 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 information

Reinforcement. Function Approximation. Learning with KATJA HOFMANN. Researcher, MSR Cambridge

Reinforcement. 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 information

Reinforcement Learning

Reinforcement 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 information

Notes on Reinforcement Learning

Notes on Reinforcement Learning 1 Introduction Notes on Reinforcement Learning Paulo Eduardo Rauber 2014 Reinforcement learning is the study of agents that act in an environment with the goal of maximizing cumulative reward signals.

More information

Reinforcement Learning. George Konidaris

Reinforcement Learning. George Konidaris Reinforcement Learning George Konidaris gdk@cs.brown.edu Fall 2017 Machine Learning Subfield of AI concerned with learning from data. Broadly, using: Experience To Improve Performance On Some Task (Tom

More information

Reinforcement Learning

Reinforcement 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 information

MDP Preliminaries. Nan Jiang. February 10, 2019

MDP 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 information

Decision Theory: Q-Learning

Decision 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 information

O 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 : 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 information

Combining PPO and Evolutionary Strategies for Better Policy Search

Combining 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 information

Actor-critic methods. Dialogue Systems Group, Cambridge University Engineering Department. February 21, 2017

Actor-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 information

Reinforcement Learning

Reinforcement 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 information

Internet Monetization

Internet 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 information

1 Introduction 2. 4 Q-Learning The Q-value The Temporal Difference The whole Q-Learning process... 5

1 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 information

Reinforcement Learning: the basics

Reinforcement 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 information

Real Time Value Iteration and the State-Action Value Function

Real 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 information

Introduction of Reinforcement Learning

Introduction 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 information

Lecture 1: March 7, 2018

Lecture 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 information

Reinforcement Learning

Reinforcement 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 information

Contributions to deep reinforcement learning and its applications in smartgrids

Contributions to deep reinforcement learning and its applications in smartgrids 1/60 Contributions to deep reinforcement learning and its applications in smartgrids Vincent François-Lavet University of Liege, Belgium September 11, 2017 Motivation 2/60 3/60 Objective From experience

More information

Temporal difference learning

Temporal difference learning Temporal difference learning AI & Agents for IET Lecturer: S Luz http://www.scss.tcd.ie/~luzs/t/cs7032/ February 4, 2014 Recall background & assumptions Environment is a finite MDP (i.e. A and S are finite).

More information

Approximate Dynamic Programming

Approximate 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 information

Off-Policy Actor-Critic

Off-Policy Actor-Critic Off-Policy Actor-Critic Ludovic Trottier Laval University July 25 2012 Ludovic Trottier (DAMAS Laboratory) Off-Policy Actor-Critic July 25 2012 1 / 34 Table of Contents 1 Reinforcement Learning Theory

More information

Reinforcement Learning In Continuous Time and Space

Reinforcement Learning In Continuous Time and Space Reinforcement Learning In Continuous Time and Space presentation of paper by Kenji Doya Leszek Rybicki lrybicki@mat.umk.pl 18.07.2008 Leszek Rybicki lrybicki@mat.umk.pl Reinforcement Learning In Continuous

More information

Approximate Dynamic Programming

Approximate 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 information

Reinforcement Learning

Reinforcement Learning Reinforcement Learning Temporal Difference Learning Temporal difference learning, TD prediction, Q-learning, elibigility traces. (many slides from Marc Toussaint) Vien Ngo Marc Toussaint University of

More information

Deterministic Policy Gradient, Advanced RL Algorithms

Deterministic 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 information

Decoupling 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 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 information

CS599 Lecture 1 Introduction To RL

CS599 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 information

arxiv: v1 [cs.lg] 20 Jun 2018

arxiv: v1 [cs.lg] 20 Jun 2018 RUDDER: Return Decomposition for Delayed Rewards arxiv:1806.07857v1 [cs.lg 20 Jun 2018 Jose A. Arjona-Medina Michael Gillhofer Michael Widrich Thomas Unterthiner Sepp Hochreiter LIT AI Lab Institute for

More information

Reinforcement Learning. Donglin Zeng, Department of Biostatistics, University of North Carolina

Reinforcement 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 information

Learning Dexterity Matthias Plappert SEPTEMBER 6, 2018

Learning 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 information

Reinforcement Learning II

Reinforcement Learning II Reinforcement Learning II Andrea Bonarini Artificial Intelligence and Robotics Lab Department of Electronics and Information Politecnico di Milano E-mail: bonarini@elet.polimi.it URL:http://www.dei.polimi.it/people/bonarini

More information

Prof. Dr. Ann Nowé. Artificial Intelligence Lab ai.vub.ac.be

Prof. Dr. Ann Nowé. Artificial Intelligence Lab ai.vub.ac.be REINFORCEMENT LEARNING AN INTRODUCTION Prof. Dr. Ann Nowé Artificial Intelligence Lab ai.vub.ac.be REINFORCEMENT LEARNING WHAT IS IT? What is it? Learning from interaction Learning about, from, and while

More information

CSC321 Lecture 22: Q-Learning

CSC321 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 information

CS 287: Advanced Robotics Fall Lecture 14: Reinforcement Learning with Function Approximation and TD Gammon case study

CS 287: Advanced Robotics Fall Lecture 14: Reinforcement Learning with Function Approximation and TD Gammon case study CS 287: Advanced Robotics Fall 2009 Lecture 14: Reinforcement Learning with Function Approximation and TD Gammon case study Pieter Abbeel UC Berkeley EECS Assignment #1 Roll-out: nice example paper: X.

More information

Reinforcement learning an introduction

Reinforcement learning an introduction Reinforcement learning an introduction Prof. Dr. Ann Nowé Computational Modeling Group AIlab ai.vub.ac.be November 2013 Reinforcement Learning What is it? Learning from interaction Learning about, from,

More information

Human-level control through deep reinforcement. Liia Butler

Human-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 information

, and rewards and transition matrices as shown below:

, and rewards and transition matrices as shown below: CSE 50a. Assignment 7 Out: Tue Nov Due: Thu Dec Reading: Sutton & Barto, Chapters -. 7. Policy improvement Consider the Markov decision process (MDP) with two states s {0, }, two actions a {0, }, discount

More information

Supplementary Material for Asynchronous Methods for Deep Reinforcement Learning

Supplementary Material for Asynchronous Methods for Deep Reinforcement Learning Supplementary Material for Asynchronous Methods for Deep Reinforcement Learning May 2, 216 1 Optimization Details We investigated two different optimization algorithms with our asynchronous framework stochastic

More information

ilstd: Eligibility Traces and Convergence Analysis

ilstd: 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 information

arxiv: v2 [cs.lg] 2 Oct 2018

arxiv: 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 information

Towards Generalization and Simplicity in Continuous Control

Towards 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 information

Approximation Methods in Reinforcement Learning

Approximation Methods in Reinforcement Learning 2018 CS420, Machine Learning, Lecture 12 Approximation Methods in Reinforcement Learning Weinan Zhang Shanghai Jiao Tong University http://wnzhang.net http://wnzhang.net/teaching/cs420/index.html Reinforcement

More information

Introduction to Reinforcement Learning

Introduction 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

Bridging the Gap Between Value and Policy Based Reinforcement Learning

Bridging the Gap Between Value and Policy Based Reinforcement Learning Bridging the Gap Between Value and Policy Based Reinforcement Learning Ofir Nachum 1 Mohammad Norouzi Kelvin Xu 1 Dale Schuurmans {ofirnachum,mnorouzi,kelvinxx}@google.com, daes@ualberta.ca Google Brain

More information