Reinforcement Learning and Deep Reinforcement Learning
|
|
- Vernon Phillips
- 5 years ago
- Views:
Transcription
1 Reinforcement Learning and Deep Reinforcement Learning Ashis Kumer Biswas, Ph.D. Deep Learning November 5, / 64
2 Outlines 1 Principles of Reinforcement Learning 2 The Q value 3 Q-learning example 4 Q-learning in Python 5 Non-deterministic Environment 6 Temporal difference Learning 7 Q-learning on OpenAI Gym 8 Deep Q-network (DQN) 9 DQN on Keras 10 Double DQN (DDQN) Deep Learning November 5, / 64
3 Outlines 1 Principles of Reinforcement Learning 2 The Q value 3 Q-learning example 4 Q-learning in Python 5 Non-deterministic Environment 6 Temporal difference Learning 7 Q-learning on OpenAI Gym 8 Deep Q-network (DQN) 9 DQN on Keras 10 Double DQN (DDQN) Deep Learning November 5, / 64
4 X=42 Reinforcement Learning Interpreter Environment Reward Action 1 An agent takes an action in an environment. State Agent Figure: The perception-action-learning loop. Image source Deep Learning November 5, / 64
5 X=42 Reinforcement Learning Interpreter Environment Reward State Agent Action Figure: The perception-action-learning loop. Image source 1 An agent takes an action in an environment. 2 That action is interpreted into a reward, R and a representation of the state, S. Deep Learning November 5, / 64
6 X=42 Reinforcement Learning Interpreter Environment Reward State Agent Action Figure: The perception-action-learning loop. Image source 1 An agent takes an action in an environment. 2 That action is interpreted into a reward, R and a representation of the state, S. 3 These two are then fed back into the agent. Deep Learning November 5, / 64
7 A Crawling Robot learns to crawl Figure: A Crawling robot developed by Francis wyffels. Video Link: Deep Learning November 5, / 64
8 Introduction to Markov Decision Process, MDP MDPs formally describe an environment for reinforcement learning, RL. where the environment is fully observable. That is, the current state completely characterizes the process. Almost all RL problems can be formalized as MDPs. Deep Learning November 5, / 64
9 Markov Property The future is independent of the past given the present. Definition A state S t is Markov if and only if P[S t+1 S t ] = P[S t+1 S 1,, S t ] The state captures all relevant information from the history. Once the state is known, the history may be thrown away. i.e., the state is a sufficient statistic of the future. Deep Learning November 5, / 64
10 State Transition Matrix For a Markov state, s, and the successor state s, the state transition probability is defined as: P ss = P[S t+1 = s S t = s] State transition matrix, P defines transition probabilities from all states s to all successor states, s, P 11 P 1n P =..... P n1 P nn where each row of the matrix sums to 1. Deep Learning November 5, / 64
11 Markov Process A Markov Process is a memoryless random process, i.e., a sequence of random states S 1, S 2,, with the Markov property. Definition A Markov Process (or Markov Chain) is a tuple, S, P, such that: S is a finite set of states. P is a state transition probability matrix: P ss = P[S t+1 = s S t = s] Deep Learning November 5, / 64
12 Example: Student Markov Chain Sample episodes for Student Markov Chain starting from S 1 = C1. C1, C2, C3, Pass, Sleep Deep Learning November 5, / 64
13 Example: Student Markov Chain Sample episodes for Student Markov Chain starting from S 1 = C1. C1, C2, C3, Pass, Sleep C1, FB, FB, C1, C2, Sleep Deep Learning November 5, / 64
14 Example: Student Markov Chain Sample episodes for Student Markov Chain starting from S 1 = C1. C1, C2, C3, Pass, Sleep C1, FB, FB, C1, C2, Sleep C1, C2, C3, Pub, C2, C3, Pass, Sleep Deep Learning November 5, / 64
15 Example: Student Markov Chain Sample episodes for Student Markov Chain starting from S 1 = C1. C1, C2, C3, Pass, Sleep C1, FB, FB, C1, C2, Sleep C1, C2, C3, Pub, C2, C3, Pass, Sleep C1, FB, FB, C1, C2, C3, Pub, C1, FB, FB, FB, C1, C2, C3, Pub, C2, Sleep Deep Learning November 5, / 64
16 Example: Student Markov Chain Deep Learning November 5, / 64
17 Markov Reward Process, MRP A Markov reward process is a Markov Chain with values. Definition A Markov Reward Process is a tuple S, P, R, γ Deep Learning November 5, / 64
18 Markov Reward Process, MRP A Markov reward process is a Markov Chain with values. Definition A Markov Reward Process is a tuple S, P, R, γ S is a finite set of states. P is a state transition probability matrix, P ss = P[S t+1 = s S t = s] Deep Learning November 5, / 64
19 Markov Reward Process, MRP A Markov reward process is a Markov Chain with values. Definition A Markov Reward Process is a tuple S, P, R, γ S is a finite set of states. P is a state transition probability matrix, P ss = P[S t+1 = s S t = s] R is a reward function, R s = E[R t+1 S t = s] Deep Learning November 5, / 64
20 Markov Reward Process, MRP A Markov reward process is a Markov Chain with values. Definition A Markov Reward Process is a tuple S, P, R, γ S is a finite set of states. P is a state transition probability matrix, P ss = P[S t+1 = s S t = s] R is a reward function, R s = E[R t+1 S t = s] γ is a discount factor, γ [0, 1] Deep Learning November 5, / 64
21 The Student MRP Deep Learning November 5, / 64
22 Return Definition The return, G t is the total discounted reward from time-step t: G t = R t+1 + γr t+2 + γ 2 R t+3 = γ k R t+k+1 k=0 The discount, γ [0, 1] is the present value of future rewards. The value of receiving reward, R after k + 1 time-steps is γ k R. This values immediate reward above delayed reward: γ close to 0 leads to myopic evaluation. γ close to 1 leads to far-sighted evaluation. Deep Learning November 5, / 64
23 Why discount? Most Markov reward and decision processes are discounted. Why? Avoids infinite returns in cyclic Markov Processes. Uncertainty about the future may not be fully represented. If the reward is financial, immediate rewards may earn more interest than delayed rewards. Animal/human behavior shows preference for immediate reward. Deep Learning November 5, / 64
24 Value function The value function v(s) gives the long-term value of state s. Definition The state value function v(s) of an MRP is the expected return starting from state s: v(s) = E[G t S t = s] Deep Learning November 5, / 64
25 The Student MRP Sample returns for Student MRP, starting from S 1 = C1 with γ = 0.5 G 1 = R 2 + γr 3 + C1, C2, C3, Pass, Sleep v 1 = = 2.25 Deep Learning November 5, / 64
26 The Student MRP Sample returns for Student MRP, starting from S 1 = C1 with γ = 0.5 G 1 = R 2 + γr 3 + C1, FB, FB, C1, C2, Sleep v 1 = = Deep Learning November 5, / 64
27 The Student MRP Sample returns for Student MRP, starting from S 1 = C1 with γ = 0.5 G 1 = R 2 + γr 3 + C1, FB, FB, C1, C2, Sleep v 1 = = Deep Learning November 5, / 64
28 State-Value function for Student MRP (γ = 0) A myopic evaluation!!! Deep Learning November 5, / 64
29 State-Value function for Student MRP (γ = 0.9) Deep Learning November 5, / 64
30 State-Value function for Student MRP (γ = 1) A far-sighted evaluation!!! Deep Learning November 5, / 64
31 Bellman Equation for MRPs The value function, v(s) can be decomposed into two parts: immediate reward, R t+1. Deep Learning November 5, / 64
32 Bellman Equation for MRPs The value function, v(s) can be decomposed into two parts: immediate reward, R t+1. discounted value of successor state γv(s t+1 ) Deep Learning November 5, / 64
33 Bellman Equation for MRPs The value function, v(s) can be decomposed into two parts: immediate reward, R t+1. discounted value of successor state γv(s t+1 ) v(s) = E[G t S t = s] = E[R t+1 + γr t+2 + γ 2 R t+3 + S t = s] = E[R t+1 + γ(r t+2 + γr t+3 + ) S t = s] = E[R t+1 + γg t+1 S t = s] = E[R t+1 + γv(s t+1 ) S t = s] Deep Learning November 5, / 64
34 Bellman Equation for MRPs it can be represented as: v(s) = E[R t+1 + γv(s t+1 ) S t = s] v(s) = R s + γ s S P ss v(s ) Deep Learning November 5, / 64
35 Bellman Equation for Student MRP Deep Learning November 5, / 64
36 Bellman Equation in Matrix Form The Bellman equation can be expressed concisely using matrices, v = R + γpv where, v is a column vector with one entry per state. v(1). v(n) = R 1 P 11 P 1n v(1). + γ R n P n1 P nn v(n) Deep Learning November 5, / 64
37 Solving the Bellman Equation It is a linear equation. Deep Learning November 5, / 64
38 Solving the Bellman Equation It is a linear equation. It can be solved directly:: v = R + γpv (1 γp)v = R v = (1 γp) 1 R Deep Learning November 5, / 64
39 Solving the Bellman Equation It is a linear equation. It can be solved directly:: v = R + γpv (1 γp)v = R v = (1 γp) 1 R Computational complexity is O(n 3 ) for n states. Direct solution only possible for small MRPs. Deep Learning November 5, / 64
40 Solving the Bellman Equation It is a linear equation. It can be solved directly:: v = R + γpv (1 γp)v = R v = (1 γp) 1 R Computational complexity is O(n 3 ) for n states. Direct solution only possible for small MRPs. There are iterative solutions for large MRPs developed: Dynamic Programming Deep Learning November 5, / 64
41 Solving the Bellman Equation It is a linear equation. It can be solved directly:: v = R + γpv (1 γp)v = R v = (1 γp) 1 R Computational complexity is O(n 3 ) for n states. Direct solution only possible for small MRPs. There are iterative solutions for large MRPs developed: Dynamic Programming Monte-Carlo Evaluation Deep Learning November 5, / 64
42 Solving the Bellman Equation It is a linear equation. It can be solved directly:: v = R + γpv (1 γp)v = R v = (1 γp) 1 R Computational complexity is O(n 3 ) for n states. Direct solution only possible for small MRPs. There are iterative solutions for large MRPs developed: Dynamic Programming Monte-Carlo Evaluation Temporal Difference Learning Deep Learning November 5, / 64
43 Markov Decision Process, MDP A Markov Decision Process, MDP is a Markov Reward Process with decisions. It is an environment in which all states are Markov. Definition A Markov Decision Process is a tuple S, A, P, R, γ Deep Learning November 5, / 64
44 Markov Decision Process, MDP A Markov Decision Process, MDP is a Markov Reward Process with decisions. It is an environment in which all states are Markov. Definition A Markov Decision Process is a tuple S, A, P, R, γ S is a finite set of states. Deep Learning November 5, / 64
45 Markov Decision Process, MDP A Markov Decision Process, MDP is a Markov Reward Process with decisions. It is an environment in which all states are Markov. Definition A Markov Decision Process is a tuple S, A, P, R, γ S is a finite set of states. A is a finite set of actions. Deep Learning November 5, / 64
46 Markov Decision Process, MDP A Markov Decision Process, MDP is a Markov Reward Process with decisions. It is an environment in which all states are Markov. Definition A Markov Decision Process is a tuple S, A, P, R, γ S is a finite set of states. A is a finite set of actions. P is a state transition probability matrix, P a ss = P[S t+1 = s S t = s, A t = a] Deep Learning November 5, / 64
47 Markov Decision Process, MDP A Markov Decision Process, MDP is a Markov Reward Process with decisions. It is an environment in which all states are Markov. Definition A Markov Decision Process is a tuple S, A, P, R, γ S is a finite set of states. A is a finite set of actions. P is a state transition probability matrix, P a ss = P[S t+1 = s S t = s, A t = a] R is a reward function, R a s = E[R t+1 S t = s, A t = a] Deep Learning November 5, / 64
48 Markov Decision Process, MDP A Markov Decision Process, MDP is a Markov Reward Process with decisions. It is an environment in which all states are Markov. Definition A Markov Decision Process is a tuple S, A, P, R, γ S is a finite set of states. A is a finite set of actions. P is a state transition probability matrix, P a ss = P[S t+1 = s S t = s, A t = a] R is a reward function, R a s = E[R t+1 S t = s, A t = a] γ is a discount factor, γ [0, 1] Deep Learning November 5, / 64
49 Student Markov Process Deep Learning November 5, / 64
50 Student Markov Reward Process, MRP Deep Learning November 5, / 64
51 Student Markov Decision Process, MDP Deep Learning November 5, / 64
52 Policies (1 of 2) Definition A policy, π is a distribution over actions given states, π(a s) = P[A t = a S t = s] A policy fully defines the behavior of an agent. MDP policies depend on the current state (and not the history). That is, policies are stationary (time independent), A t π(. s t ), t > 0 Deep Learning November 5, / 64
53 Policies (2 of 2) Given an MDP, M = S, A, P, R, γ, and a policy, π The state sequence S 1, S 2, is a Markov process S, P π The state and reward sequence S 1, R 2, S 2, is a Markov Reward Process, MRP: S, P π, R π, γ, where P π ss = a A π(a s)p a ss R π s = a A π(a s)r a s Deep Learning November 5, / 64
54 Value Functions Definition The state-value function, v π (s) of an MDP is the expected return starting from state s, and then following policy π. v π (s) = E π [G t S t = s] Deep Learning November 5, / 64
55 Value Functions Definition The state-value function, v π (s) of an MDP is the expected return starting from state s, and then following policy π. v π (s) = E π [G t S t = s] Definition The action-value function q π (s, a) is the expected return starting from state s, taking action a, and then following policy π. q π (s, a) = E π [G t S t = s, A t = a] Deep Learning November 5, / 64
56 Example: State-Value Function for Student MDP Deep Learning November 5, / 64
57 Bellman Expectation Equation The state-value function can again be decomposed into immediate reward plus discounted value of successor state, v π (s) = E π [R t+1 + γv π (S t+1 ) S t = s] The action-value function can also be decomposed as, q π (s, a) = E π [R t+1 + γq π (S t+1, A t+1 ) S t = s, A t = a] Deep Learning November 5, / 64
58 Bellman Expectation Equation for v π (.) v π (s) = a A π(a s)q π (s, a) Deep Learning November 5, / 64
59 Bellman Expectation Equation for q π (.) (1 of 2) q π (s, a) = R a s + γ s S P a ss v π(s ) Deep Learning November 5, / 64
60 Bellman Expectation Equation for v π (.) v π (s) = π(a s) R a s + γ Pss a v π(s ) a A s S Deep Learning November 5, / 64
61 Bellman Expectation Equation for q π (.) (2 of 2) q π (s, a) = R a s + γ s S Pss a π(a s )q π (s, a ) a A Deep Learning November 5, / 64
62 Bellman Expectation Equation in Student MDP Deep Learning November 5, / 64
63 Optimal Value Function Definition The optimal state-value function, v (s) is the maximum state-value function over all policies v (s) = max π v π (s) Definition The optimal action-value function, q (s, a) is the maximum action-value function over all policies q (s, a) = max π q π (s, a) The optimal value function specifies the best possible performance in the MDP. An MDP is considered solved when we know the optimal value function. Deep Learning November 5, / 64
64 Optimal State-Value function for the Student MDP Deep Learning November 5, / 64
65 Optimal Action-Value function for the Student MDP Deep Learning November 5, / 64
66 Optimal Policy It defines a partial ordering over the policies, π π if v π (s) v π (s), s Theorem For any Markov Decision Process, There exists an optimal policy, π that is better than or equal to all other policies, π π, π. All optimal policies achieve the optimal state value function, v π (s) = v (s) All optimal policies achieve the optimal action value function, q π (s, a) = q (s, a) Deep Learning November 5, / 64
67 Finding an optimal policy An optimal policy can be found by maximizing over q (s, a), 1 if a = argmax q (s, a) π (a s) = a A 0 otherwise There is always a deterinistic optimal policy for any MDP. If we know q (s, a), we immediately have the optimal policy. Deep Learning November 5, / 64
68 Example: Optimal Policy for the Student MDP Deep Learning November 5, / 64
69 Bellman Optimality Equation for v The optimal value functions are recursively related by the Bellman optimality equations: v (s) = max a q (s, a) Deep Learning November 5, / 64
70 Bellman Optimality Equation for q q (s, a) = R a s + γ s S P a ss v (s ) Deep Learning November 5, / 64
71 Bellman Optimality Equation for v (2) v (s) = max a R a s + γ Pss a v (s ) s S Deep Learning November 5, / 64
72 Bellman Optimality Equation for q (2) q (s, a) = R a s + γ s S P a ss max a q (s, a ) Deep Learning November 5, / 64
73 Bellman Optimality Equation for the Student MDP Deep Learning November 5, / 64
74 Solving the Bellman Optimality Equation Bellman Optimality Equation is non-linear. No closed form solution (in general). However, many iterative solution available: Policy gradient Q-learning SARSA Deep Learning November 5, / 64
75 Outlines 1 Principles of Reinforcement Learning 2 The Q value 3 Q-learning example 4 Q-learning in Python 5 Non-deterministic Environment 6 Temporal difference Learning 7 Q-learning on OpenAI Gym 8 Deep Q-network (DQN) 9 DQN on Keras 10 Double DQN (DDQN) Deep Learning November 5, / 64
76 The Q value How to find the optimal π? How does the agent learn by interacting with the environment? Instead of finding the policy that maximizes the state-value for all states, find the action that maximizes the Q value for all states. Deep Learning November 5, / 64
77 Outlines 1 Principles of Reinforcement Learning 2 The Q value 3 Q-learning example 4 Q-learning in Python 5 Non-deterministic Environment 6 Temporal difference Learning 7 Q-learning on OpenAI Gym 8 Deep Q-network (DQN) 9 DQN on Keras 10 Double DQN (DDQN) Deep Learning November 5, / 64
78 Outlines 1 Principles of Reinforcement Learning 2 The Q value 3 Q-learning example 4 Q-learning in Python 5 Non-deterministic Environment 6 Temporal difference Learning 7 Q-learning on OpenAI Gym 8 Deep Q-network (DQN) 9 DQN on Keras 10 Double DQN (DDQN) Deep Learning November 5, / 64
79 Outlines 1 Principles of Reinforcement Learning 2 The Q value 3 Q-learning example 4 Q-learning in Python 5 Non-deterministic Environment 6 Temporal difference Learning 7 Q-learning on OpenAI Gym 8 Deep Q-network (DQN) 9 DQN on Keras 10 Double DQN (DDQN) Deep Learning November 5, / 64
80 Outlines 1 Principles of Reinforcement Learning 2 The Q value 3 Q-learning example 4 Q-learning in Python 5 Non-deterministic Environment 6 Temporal difference Learning 7 Q-learning on OpenAI Gym 8 Deep Q-network (DQN) 9 DQN on Keras 10 Double DQN (DDQN) Deep Learning November 5, / 64
81 Outlines 1 Principles of Reinforcement Learning 2 The Q value 3 Q-learning example 4 Q-learning in Python 5 Non-deterministic Environment 6 Temporal difference Learning 7 Q-learning on OpenAI Gym 8 Deep Q-network (DQN) 9 DQN on Keras 10 Double DQN (DDQN) Deep Learning November 5, / 64
82 Outlines 1 Principles of Reinforcement Learning 2 The Q value 3 Q-learning example 4 Q-learning in Python 5 Non-deterministic Environment 6 Temporal difference Learning 7 Q-learning on OpenAI Gym 8 Deep Q-network (DQN) 9 DQN on Keras 10 Double DQN (DDQN) Deep Learning November 5, / 64
83 Outlines 1 Principles of Reinforcement Learning 2 The Q value 3 Q-learning example 4 Q-learning in Python 5 Non-deterministic Environment 6 Temporal difference Learning 7 Q-learning on OpenAI Gym 8 Deep Q-network (DQN) 9 DQN on Keras 10 Double DQN (DDQN) Deep Learning November 5, / 64
84 Outlines 1 Principles of Reinforcement Learning 2 The Q value 3 Q-learning example 4 Q-learning in Python 5 Non-deterministic Environment 6 Temporal difference Learning 7 Q-learning on OpenAI Gym 8 Deep Q-network (DQN) 9 DQN on Keras 10 Double DQN (DDQN) Deep Learning November 5, / 64
85 Thanks Questions? Deep Learning November 5, / 64
Lecture 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 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 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 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 informationPART A and ONE question from PART B; or ONE question from PART A and TWO questions from PART B.
Advanced Topics in Machine Learning, GI13, 2010/11 Advanced Topics in Machine Learning, GI13, 2010/11 Answer any THREE questions. Each question is worth 20 marks. Use separate answer books Answer any THREE
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 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 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. 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 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 informationReinforcement Learning
Reinforcement Learning Dipendra Misra Cornell University dkm@cs.cornell.edu https://dipendramisra.wordpress.com/ Task Grasp the green cup. Output: Sequence of controller actions Setup from Lenz et. al.
More informationThis question has three parts, each of which can be answered concisely, but be prepared to explain and justify your concise answer.
This question has three parts, each of which can be answered concisely, but be prepared to explain and justify your concise answer. 1. Suppose you have a policy and its action-value function, q, then you
More informationGrundlagen der Künstlichen Intelligenz
Grundlagen der Künstlichen Intelligenz Reinforcement learning Daniel Hennes 4.12.2017 (WS 2017/18) University Stuttgart - IPVS - Machine Learning & Robotics 1 Today Reinforcement learning Model based and
More 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 informationMachine Learning. Reinforcement learning. Hamid Beigy. Sharif University of Technology. Fall 1396
Machine Learning Reinforcement learning Hamid Beigy Sharif University of Technology Fall 1396 Hamid Beigy (Sharif University of Technology) Machine Learning Fall 1396 1 / 32 Table of contents 1 Introduction
More informationReinforcement Learning
Reinforcement Learning Markov decision process & Dynamic programming Evaluative feedback, value function, Bellman equation, optimality, Markov property, Markov decision process, dynamic programming, value
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 informationDecision Theory: Q-Learning
Decision Theory: Q-Learning CPSC 322 Decision Theory 5 Textbook 12.5 Decision Theory: Q-Learning CPSC 322 Decision Theory 5, Slide 1 Lecture Overview 1 Recap 2 Asynchronous Value Iteration 3 Q-Learning
More informationDecision Theory: Markov Decision Processes
Decision Theory: Markov Decision Processes CPSC 322 Lecture 33 March 31, 2006 Textbook 12.5 Decision Theory: Markov Decision Processes CPSC 322 Lecture 33, Slide 1 Lecture Overview Recap Rewards and Policies
More informationMarkov Decision Processes and Solving Finite Problems. February 8, 2017
Markov Decision Processes and Solving Finite Problems February 8, 2017 Overview of Upcoming Lectures Feb 8: Markov decision processes, value iteration, policy iteration Feb 13: Policy gradients Feb 15:
More informationLearning Control for Air Hockey Striking using Deep Reinforcement Learning
Learning Control for Air Hockey Striking using Deep Reinforcement Learning Ayal Taitler, Nahum Shimkin Faculty of Electrical Engineering Technion - Israel Institute of Technology May 8, 2017 A. Taitler,
More informationReinforcement 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 informationReinforcement Learning and NLP
1 Reinforcement Learning and NLP Kapil Thadani kapil@cs.columbia.edu RESEARCH Outline 2 Model-free RL Markov decision processes (MDPs) Derivative-free optimization Policy gradients Variance reduction Value
More informationMarkov Decision Processes
Markov Decision Processes Noel Welsh 11 November 2010 Noel Welsh () Markov Decision Processes 11 November 2010 1 / 30 Annoucements Applicant visitor day seeks robot demonstrators for exciting half hour
More informationTemporal Difference. Learning KENNETH TRAN. Principal Research Engineer, MSR AI
Temporal Difference Learning KENNETH TRAN Principal Research Engineer, MSR AI Temporal Difference Learning Policy Evaluation Intro to model-free learning Monte Carlo Learning Temporal Difference Learning
More information(Deep) Reinforcement Learning
Martin Matyášek Artificial Intelligence Center Czech Technical University in Prague October 27, 2016 Martin Matyášek VPD, 2016 1 / 17 Reinforcement Learning in a picture R. S. Sutton and A. G. Barto 2015
More informationReinforcement Learning. 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 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 informationReinforcement Learning: An Introduction
Introduction Betreuer: Freek Stulp Hauptseminar Intelligente Autonome Systeme (WiSe 04/05) Forschungs- und Lehreinheit Informatik IX Technische Universität München November 24, 2004 Introduction What is
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 informationArtificial Intelligence
Artificial Intelligence Dynamic Programming Marc Toussaint University of Stuttgart Winter 2018/19 Motivation: So far we focussed on tree search-like solvers for decision problems. There is a second important
More informationINF 5860 Machine learning for image classification. Lecture 14: Reinforcement learning May 9, 2018
Machine learning for image classification Lecture 14: Reinforcement learning May 9, 2018 Page 3 Outline Motivation Introduction to reinforcement learning (RL) Value function based methods (Q-learning)
More 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 informationMachine Learning I Reinforcement Learning
Machine Learning I Reinforcement Learning Thomas Rückstieß Technische Universität München December 17/18, 2009 Literature Book: Reinforcement Learning: An Introduction Sutton & Barto (free online version:
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 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 informationTrust Region Policy Optimization
Trust Region Policy Optimization Yixin Lin Duke University yixin.lin@duke.edu March 28, 2017 Yixin Lin (Duke) TRPO March 28, 2017 1 / 21 Overview 1 Preliminaries Markov Decision Processes Policy iteration
More 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 information, 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 informationDueling Network Architectures for Deep Reinforcement Learning (ICML 2016)
Dueling Network Architectures for Deep Reinforcement Learning (ICML 2016) Yoonho Lee Department of Computer Science and Engineering Pohang University of Science and Technology October 11, 2016 Outline
More 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 informationTemporal 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 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 informationCMU Lecture 12: Reinforcement Learning. Teacher: Gianni A. Di Caro
CMU 15-781 Lecture 12: Reinforcement Learning Teacher: Gianni A. Di Caro REINFORCEMENT LEARNING Transition Model? State Action Reward model? Agent Goal: Maximize expected sum of future rewards 2 MDP PLANNING
More informationReinforcement Learning Part 2
Reinforcement Learning Part 2 Dipendra Misra Cornell University dkm@cs.cornell.edu https://dipendramisra.wordpress.com/ From previous tutorial Reinforcement Learning Exploration No supervision Agent-Reward-Environment
More information6 Reinforcement Learning
6 Reinforcement Learning As discussed above, a basic form of supervised learning is function approximation, relating input vectors to output vectors, or, more generally, finding density functions p(y,
More informationNotes 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 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 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 informationQ-Learning in Continuous State Action Spaces
Q-Learning in Continuous State Action Spaces Alex Irpan alexirpan@berkeley.edu December 5, 2015 Contents 1 Introduction 1 2 Background 1 3 Q-Learning 2 4 Q-Learning In Continuous Spaces 4 5 Experimental
More informationReinforcement 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 informationReinforcement Learning. Summer 2017 Defining MDPs, Planning
Reinforcement Learning Summer 2017 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 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 informationLecture 8: Policy Gradient
Lecture 8: Policy Gradient Hado van Hasselt Outline 1 Introduction 2 Finite Difference Policy Gradient 3 Monte-Carlo Policy Gradient 4 Actor-Critic Policy Gradient Introduction Vapnik s rule Never solve
More informationCSC321 Lecture 22: Q-Learning
CSC321 Lecture 22: Q-Learning Roger Grosse Roger Grosse CSC321 Lecture 22: Q-Learning 1 / 21 Overview Second of 3 lectures on reinforcement learning Last time: policy gradient (e.g. REINFORCE) Optimize
More informationLecture 7: Value Function Approximation
Lecture 7: Value Function Approximation Joseph Modayil Outline 1 Introduction 2 3 Batch Methods Introduction Large-Scale Reinforcement Learning Reinforcement learning can be used to solve large problems,
More 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 informationAn Introduction to Reinforcement Learning
1 / 58 An Introduction to Reinforcement Learning Lecture 01: Introduction Dr. Johannes A. Stork School of Computer Science and Communication KTH Royal Institute of Technology January 19, 2017 2 / 58 ../fig/reward-00.jpg
More informationOff-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 informationPolicy Gradient Methods. February 13, 2017
Policy Gradient Methods February 13, 2017 Policy Optimization Problems maximize E π [expression] π Fixed-horizon episodic: T 1 Average-cost: lim T 1 T r t T 1 r t Infinite-horizon discounted: γt r t Variable-length
More informationMachine Learning. Machine Learning: Jordan Boyd-Graber University of Maryland REINFORCEMENT LEARNING. Slides adapted from Tom Mitchell and Peter Abeel
Machine Learning Machine Learning: Jordan Boyd-Graber University of Maryland REINFORCEMENT LEARNING Slides adapted from Tom Mitchell and Peter Abeel Machine Learning: Jordan Boyd-Graber UMD Machine Learning
More informationLecture 3: Policy Evaluation Without Knowing How the World Works / Model Free Policy Evaluation
Lecture 3: Policy Evaluation Without Knowing How the World Works / Model Free Policy Evaluation CS234: RL Emma Brunskill Winter 2018 Material builds on structure from David SIlver s Lecture 4: Model-Free
More informationLearning to Control an Octopus Arm with Gaussian Process Temporal Difference Methods
Learning to Control an Octopus Arm with Gaussian Process Temporal Difference Methods Yaakov Engel Joint work with Peter Szabo and Dmitry Volkinshtein (ex. Technion) Why use GPs in RL? A Bayesian approach
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 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 informationLecture 17: Reinforcement Learning, Finite Markov Decision Processes
CSE599i: Online and Adaptive Machine Learning Winter 2018 Lecture 17: Reinforcement Learning, Finite Markov Decision Processes Lecturer: Kevin Jamieson Scribes: Aida Amini, Kousuke Ariga, James Ferguson,
More informationPART A and ONE question from PART B; or ONE question from PART A and TWO questions from PART B.
Advanced Topics in Machine Learning, GI13, 2010/11 Advanced Topics in Machine Learning, GI13, 2010/11 Answer any THREE questions. Each question is worth 20 marks. Use separate answer books Answer any THREE
More informationLecture 23: Reinforcement Learning
Lecture 23: Reinforcement Learning MDPs revisited Model-based learning Monte Carlo value function estimation Temporal-difference (TD) learning Exploration November 23, 2006 1 COMP-424 Lecture 23 Recall:
More informationMachine Learning I Continuous Reinforcement Learning
Machine Learning I Continuous Reinforcement Learning Thomas Rückstieß Technische Universität München January 7/8, 2010 RL Problem Statement (reminder) state s t+1 ENVIRONMENT reward r t+1 new step r t
More informationReinforcement Learning with Function Approximation. Joseph Christian G. Noel
Reinforcement Learning with Function Approximation Joseph Christian G. Noel November 2011 Abstract Reinforcement learning (RL) is a key problem in the field of Artificial Intelligence. The main goal is
More informationLecture 25: Learning 4. Victor R. Lesser. CMPSCI 683 Fall 2010
Lecture 25: Learning 4 Victor R. Lesser CMPSCI 683 Fall 2010 Final Exam Information Final EXAM on Th 12/16 at 4:00pm in Lederle Grad Res Ctr Rm A301 2 Hours but obviously you can leave early! Open Book
More informationReinforcement Learning via Policy Optimization
Reinforcement Learning via Policy Optimization Hanxiao Liu November 22, 2017 1 / 27 Reinforcement Learning Policy a π(s) 2 / 27 Example - Mario 3 / 27 Example - ChatBot 4 / 27 Applications - Video Games
More 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 informationReinforcement Learning: the basics
Reinforcement Learning: the basics Olivier Sigaud Université Pierre et Marie Curie, PARIS 6 http://people.isir.upmc.fr/sigaud August 6, 2012 1 / 46 Introduction Action selection/planning Learning by trial-and-error
More informationThe Reinforcement Learning Problem
The Reinforcement Learning Problem Slides based on the book Reinforcement Learning by Sutton and Barto Formalizing Reinforcement Learning Formally, the agent and environment interact at each of a sequence
More informationReinforcement Learning
Reinforcement Learning Temporal Difference Learning Temporal difference learning, TD prediction, Q-learning, elibigility traces. (many slides from Marc Toussaint) Vien Ngo MLR, University of Stuttgart
More informationVariance Reduction for Policy Gradient Methods. March 13, 2017
Variance Reduction for Policy Gradient Methods March 13, 2017 Reward Shaping Reward Shaping Reward Shaping Reward shaping: r(s, a, s ) = r(s, a, s ) + γφ(s ) Φ(s) for arbitrary potential Φ Theorem: r admits
More informationReinforcement Learning for NLP
Reinforcement Learning for NLP Advanced Machine Learning for NLP Jordan Boyd-Graber REINFORCEMENT OVERVIEW, POLICY GRADIENT Adapted from slides by David Silver, Pieter Abbeel, and John Schulman Advanced
More informationReinforcement 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 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 informationCS788 Dialogue Management Systems Lecture #2: Markov Decision Processes
CS788 Dialogue Management Systems Lecture #2: Markov Decision Processes Kee-Eung Kim KAIST EECS Department Computer Science Division Markov Decision Processes (MDPs) A popular model for sequential decision
More informationDeep Reinforcement Learning: Policy Gradients and Q-Learning
Deep Reinforcement Learning: Policy Gradients and Q-Learning John Schulman Bay Area Deep Learning School September 24, 2016 Introduction and Overview Aim of This Talk What is deep RL, and should I use
More informationAdministration. CSCI567 Machine Learning (Fall 2018) Outline. Outline. HW5 is available, due on 11/18. Practice final will also be available soon.
Administration CSCI567 Machine Learning Fall 2018 Prof. Haipeng Luo U of Southern California Nov 7, 2018 HW5 is available, due on 11/18. Practice final will also be available soon. Remaining weeks: 11/14,
More informationMultiagent Value Iteration in Markov Games
Multiagent Value Iteration in Markov Games Amy Greenwald Brown University with Michael Littman and Martin Zinkevich Stony Brook Game Theory Festival July 21, 2005 Agenda Theorem Value iteration converges
More informationProbabilistic Planning. George Konidaris
Probabilistic Planning George Konidaris gdk@cs.brown.edu Fall 2017 The Planning Problem Finding a sequence of actions to achieve some goal. Plans It s great when a plan just works but the world doesn t
More informationarxiv: 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 informationProf. 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 informationReinforcement learning
Reinforcement learning Stuart Russell, UC Berkeley Stuart Russell, UC Berkeley 1 Outline Sequential decision making Dynamic programming algorithms Reinforcement learning algorithms temporal difference
More informationMultiagent (Deep) Reinforcement Learning
Multiagent (Deep) Reinforcement Learning MARTIN PILÁT (MARTIN.PILAT@MFF.CUNI.CZ) Reinforcement learning The agent needs to learn to perform tasks in environment No prior knowledge about the effects of
More 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 /doku.php/courses/a4b33zui/start pagenda Previous lecture: individual rational
More informationCS 598 Statistical Reinforcement Learning. Nan Jiang
CS 598 Statistical Reinforcement Learning Nan Jiang Overview What s this course about? A grad-level seminar course on theory of RL 3 What s this course about? A grad-level seminar course on theory of RL
More informationHidden Markov Models (HMM) and Support Vector Machine (SVM)
Hidden Markov Models (HMM) and Support Vector Machine (SVM) Professor Joongheon Kim School of Computer Science and Engineering, Chung-Ang University, Seoul, Republic of Korea 1 Hidden Markov Models (HMM)
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 informationMotivation for introducing probabilities
for introducing probabilities Reaching the goals is often not sufficient: it is important that the expected costs do not outweigh the benefit of reaching the goals. 1 Objective: maximize benefits - costs.
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 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 informationCS230: Lecture 9 Deep Reinforcement Learning
CS230: Lecture 9 Deep Reinforcement Learning Kian Katanforoosh Menti code: 21 90 15 Today s outline I. Motivation II. Recycling is good: an introduction to RL III. Deep Q-Learning IV. Application of Deep
More informationReinforcement 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 informationDiscrete planning (an introduction)
Sistemi Intelligenti Corso di Laurea in Informatica, A.A. 2017-2018 Università degli Studi di Milano Discrete planning (an introduction) Nicola Basilico Dipartimento di Informatica Via Comelico 39/41-20135
More informationMarkov Decision Processes (and a small amount of reinforcement learning)
Markov Decision Processes (and a small amount of reinforcement learning) Slides adapted from: Brian Williams, MIT Manuela Veloso, Andrew Moore, Reid Simmons, & Tom Mitchell, CMU Nicholas Roy 16.4/13 Session
More information