Reinforcement Learning in Partially Observable Multiagent Settings: Monte Carlo Exploring Policies

Size: px
Start display at page:

Download "Reinforcement Learning in Partially Observable Multiagent Settings: Monte Carlo Exploring Policies"

Transcription

1 Reinforcement earning in Partially Observable Multiagent Settings: Monte Carlo Exploring Policies Presenter: Roi Ceren THINC ab, University of Georgia Prashant Doshi THINC ab, University of Georgia Bikramjit Banerjee University of Southern Mississippi

2 Introduction Model- free reinforcement learning in multiagent systems is a nascent field Monte Carlo Exploring Starts for POMDPs is a powerful single- agent R technique Policy iteration leveraging Q- learning to hill- climb through the local policy space to local optima Allows PAC bounds to select sample complexity with confidence

3 Introduction We extend MCES- P to the non- cooperative multiagent setting and introduce MCES for Interactive POMDPs Explicitly models the opponent Predicates action- values on expected opponent behavior When instantiated with PAC, trades off computational expense of modeling with lower sample bound complexity We additionally provide a policy space pruning mechanism to promote scalability Parametrically bounds regret from avoiding policies Prioritizes eliminating low- regret policy transformations

4 Background: Multiagent Decision Process In the multiagent setting, all agents affect the state and the reward for each agent Physical State Action Action Agent i Action (Joint) Rewards Action Agent j Reward R(s,a i,a j ) Reward

5 Background: I-POMDP The Interactive POMDP (I- POMDP) (Gmytrasiewicz and Doshi 2005) <IS,A,T,Ω,O,R> Non- cooperative: Agents get individual, potentially competitive rewards Actions A, state transitions T, observations Ω, observation probabilities O, and rewards R IS: Interactive state, combining the physical state and a model of the other agent Significant uncertainty Must reason not only the physical state, but also the opponent s motivations and beliefs

6 Background: MCES-P Template Monte Carlo Exploring Starts for POMDPs (MCES- P) (Perkins - AAAI 2002) General template Explore neighborhood of π - all policies that differ by a single action a on some observation sequence o Compute expected value by simulating policies online Hill climb to policies with better values Terminate if no neighbor is better than the current policy

7 Background: MCES-P Template Transformation Pick random observation sequence and replace with a random action o1 a2 o2 {o1,o2}: a1 à a3 o1 a2 o2 a1 a3 a1 a3 o1 o2 o1 o2 o1 o2 o1 o2 a3 a1 a2 a2 a3 a3 a2 a2

8 Background: MCES-P Template Transformation Pick random observation sequence and replace with a random action π {o1,o2}: a1 ß à a3 π '

9 Background: MCES-P Template Transformation Pick random observation sequence and replace with a random action π ' o1: a1 ß à a2 {o1,o2}: a1 ß à a2 π ' π ' o1: a1 ß à a3 π {o1,o2}: a1 ß à a3 π ' : a2 ß à a1 : a2 ß à a3 π ' π '

10 Background: MCES-P Template Transformation ocal Neighborhood

11 Background: MCES-P Template Sampling Pick random action and simulate a3 Q *,,. 1 α(m, c,,. ) Q *,,. + α m, c,,. R 9,:;<, (τ)

12 Background: MCES-P Template Sampling Sample neighborhood k times for each policy Q *? > Q * + ε π π

13 Background: MCES-P Template Sampling Sample neighborhood k times for each policy Q *? > Q * + ε π π

14 Background: MCES-P Template Sampling Sample neighborhood k times for each policy Q *? > Q * + ε

15 Background: MCES-P Template Termination When all neighbors sampled k times and no neighbor is better

16 Background: MCESP+PAC Problem: Choosing a good sample bound k ow values of k increase the chance we make errors when transforming High values, though requiring more samples, guarantee we hill- climb correctly High Error Probability ow Error Probability Inaccurate Q- values Accurate Q- values

17 Background: MCESP+PAC Solution: Pick a k that guarantees some confidence on the accuracy of the Q- value Probably Approximately Correct (PAC) earning The probability of the sample average deviating from the true mean by more than variance ε is bound by error δ Pr XG μ > ε 2 exp 2k ε Λ P = δ

18 Background: MCESP+PAC With ε and δ, we calculate required samples to satisfy the error bound m is the number of current transformations N is number of neighbor policies δ a = bc a d * d Λ π ', π max g k a = 2 Λ(π) ε P ln 2N δ a (Q * Q *?) min(q * Q *?) 2T R a.i R ajk Λ π = g max Λ(π, *? kmjnop,q * π' )

19 Background: MCESP+PAC We can transform early by modifying ε ε m, p, q = Λ π, π ' 1 2p ln 2 k a 1 N ε δ a 2 if p = q = k a otherwise if p = q < k a Terminate when k a samples of each neighbor is taken or for all neighbor policies: Q,,. < Q,,*(,) + ε ε(m, c,,., c,,*, )

20 Background: MCESP+PAC Then, with probability 1 δ 1. MCESP+PAC picks transformations that are always better than the current policy 2. MCESP+PAC terminates with a policy that is an ε- local optima That is, there is no neighbor that is better than the last policy by more than ε

21 MCES-P for Multiagent Settings MCES- P can almost be used as is in the multiagent setting Observations Public Noisily indicates physical state Private Noisily indicates other agents actions MCES- P has high computational costs arge neighborhood requiring k a samples each MCES for I- POMDPs: Explicitly models the opponent and significantly decreases sample requirements

22 MCES-IP Template MCES-P vs. MCES-IP MCES- P simulation and Q- update Pick random o and a Simulate π o, a generating τ Update Q *,,. with R 9,:;<, (τ) MCES- IP reasons about which actions the opponent took in the simulation prior to updating Pick random o and a Simulate π o, a generating τ Update belief over opponent models Calculate a x from most likely models. Update Q w *,,. with R 9,:;<, (τ)

23 MCES-IP Template Models MCES- IP maintains a set of models of the opponent, where a model = <history, policy tree> o1 a1 o2 o1 a2 o2 o1 a3 o2 a1 a1 a2 a2 a1 a2 o1 o2 o1 o2 o1 o2 o1 o2 o1 o2 o1 o2 a1 a1 a1 a1 a2 a2 a2 a2 a2 a3 a3 a1 m1 m2 m3

24 MCES-IP Template Generating a x Every round, MCES- IP updates the most probable model and selects the most probable action m1 m2 m3 t=1 t=2 t=3

25 0.4 MCES-IP Template Generating a x Every round, MCES- IP updates the most probable model and selects the most probable action 1.00 o j = 2 o = m1 m2 m3 m1 m2 m3 t=1 t=2 t=3 a j 0 = 2

26 0.40 MCES-IP Template Generating a x Every round, MCES- IP updates the most probable model and selects the most probable action 1.00 o j = 2 o = 1.00 o j = 1 o = m1 m2 m3 m1 m2 m3 m1 m2 m3 t=1 t=2 t=3 a j 0 = 2 a j 1 = 1

27 0.4 MCES-IP Template Generating a x Every round, MCES- IP updates the most probable model and selects the most probable action 1.00 o j = 2 o = 1.00 o j = 1 o = o j = 1 o = m1 m2 m3 m1 m2 m3 m1 m2 m3 m1 m2 m3 t=1 t=2 t=3 a j 0 = 2 a j 1 = 1 a j 2 = 3 a j = {2, 1, 3}

28 MCES-IP Template Updating Q-values Update counts and Q- values using a x. Q w. *,,. 1 α m, c w.,,. Q w. *,,. + α m, c w,,. R 9,:;<, (τ) So far, MCES- IP is more expensive than MCES- P The Q- table is now up to A x larger!

29 MCESIP+PAC PAC Bounds MCESIP+PAC has similar PAC bounds to MCESP+PAC k a = 2 Λ. w(π j ) ε P ln 2N δ a ε. w m, p, q = Λ.w π j, π j ' 1 2p ln 2 k a 1 N δ a ε 2 if p = q = k a otherwise if p = q < k a

30 MCESIP+PAC PAC Bounds Λ. w modifies the range of possible rewards Since the opponent action is known, the range of possible rewards may often be narrower a x 1 a x 2 a j a j resulting in the following proposition: Λ. w π j, π j ' Λ π j, π j '

31 MCESIP+PAC PAC Bounds MCESIP+PAC terminates when k a samples of the local neighborhood bears no better policy or for all neighbors π Q *? < Q * + ε ε(m, c,,., c,,*, ) With probability 1 δ 1. MCESIP+PAC picks transformations that are always better than the current policy 2. MCESIP+PAC terminates with a policy that is an ε- local optima

32 Policy Search Space Pruning

33 Policy Search Space Pruning Introduction Not all observation sequences occur with the same probability ow likelihood events are difficult to sample Pruning: Avoid policy transformations that involve rare observation sequences while considering the impact on reward Regret: The amount of expected value lost by avoiding simulating on these transformations

34 Pr 6% Pr 30% Policy Search Space Pruning Regret G regret 6.6 regret 33 G G G G G G

35 100% Allowable regret Policy Search Space Pruning G Allowed transformations G G G G G G 0%

36 100% Allowable regret Policy Search Space Pruning G Allowed transformations G G G G G G 0%

37 100% Allowable regret Policy Search Space Pruning G Allowed transformations G G G G G G 0%

38 100% Allowable regret Policy Search Space Pruning G Allowed transformations G G G G G G 0%

39 3 Domains Experiments Domains Multiagent Tiger Problem 3x2 UAV Problem

40 3 Domains Experiments Domains Placement ayering Integration bank offshore casinos insurance shell companies real estate Money aundering (M) Problem

41 3 Domains Experiments Domains Placement ayering Integration bank offshore casinos insurance shell companies real estate Money aundering (M) Problem

42 Experiments Domain Parameters Opponent follows a fixed strategy Single: Only one policy is ever used Mixed (Non- stationary environment): Randomly selects from 2 to 3 policies every new trajectory ε δ % regret horizon Multiagent Tiger % 3 3x2 UAV % 3 Money aundering % 3

43 Experiments Comparative Results Right: 2 runs comparing MCESP+PAC and MCESIP+PAC Right- top: Mixed strategy opponent Right- middle: Single strategy opponent

44 Experiments Pruning Pruning is crucial to tractability

45 Concluding Remarks Model- free R in multiagent settings Generalized from MCES- P MCES- IP models the opponent, more sample efficient when paired with PAC bounds Partially model- free Instantiated with PAC to provide ε- local optimality and search space pruning for improved scalability

46 Thank you! Q & A

47 Related Works Bayes- Adaptive POMDPs (Ross et al. 2007) Extended to MPOMDPs (Amato and Oliehoek 2013) Model- based R IMCQ- Alt for Dec- POMDPs (Banerjee et al. 2013) Quasi- model based intermediate calculation of model parameters Alternating each agent must take turns Bayes- Adaptive I- POMDPs (Ng et al. 2012) Model- based R Physical state perfectly observable

48 Background: Decision Processes Decision problem: how to optimize behavior to maximize reward? Choose the action that has the best expected outcome Agent Action Preferences Reward R(a)

49 Background : Decision Processes Physical State Action Agent Action Preferences Reward R(s,a)

50 Background : Decision Processes Physical State Action Agent Action Preferences Reward R(s,a)

51 Background: R A popular class of model- free R methods are the temporal difference learning models Example: Q- learning Q s, a; α = 1 α Q s, a + α r s, a + γ max.' Q(s, a ' ) α: earning rate γ: Discount factor Computes action- values from a state by exploring new values and exploiting previous knowledge

Marks. bonus points. } Assignment 1: Should be out this weekend. } Mid-term: Before the last lecture. } Mid-term deferred exam:

Marks. 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 information

Grundlagen der Künstlichen Intelligenz

Grundlagen der Künstlichen Intelligenz Grundlagen der Künstlichen Intelligenz Uncertainty & Probabilities & Bandits Daniel Hennes 16.11.2017 (WS 2017/18) University Stuttgart - IPVS - Machine Learning & Robotics 1 Today Uncertainty Probability

More information

Optimally Solving Dec-POMDPs as Continuous-State MDPs

Optimally Solving Dec-POMDPs as Continuous-State MDPs Optimally Solving Dec-POMDPs as Continuous-State MDPs Jilles Dibangoye (1), Chris Amato (2), Olivier Buffet (1) and François Charpillet (1) (1) Inria, Université de Lorraine France (2) MIT, CSAIL USA IJCAI

More information

Basics of reinforcement learning

Basics 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 information

This 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. 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 information

Administration. 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) 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 information

Markov decision processes

Markov 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 information

Artificial Intelligence

Artificial 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 information

Markov Decision Processes (and a small amount of reinforcement learning)

Markov 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

RL 14: Simplifications of POMDPs

RL 14: Simplifications of POMDPs RL 14: Simplifications of POMDPs Michael Herrmann University of Edinburgh, School of Informatics 04/03/2016 POMDPs: Points to remember Belief states are probability distributions over states Even if computationally

More information

MARKOV DECISION PROCESSES (MDP) AND REINFORCEMENT LEARNING (RL) Versione originale delle slide fornita dal Prof. Francesco Lo Presti

MARKOV 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 information

A Decentralized Approach to Multi-agent Planning in the Presence of Constraints and Uncertainty

A Decentralized Approach to Multi-agent Planning in the Presence of Constraints and Uncertainty 2011 IEEE International Conference on Robotics and Automation Shanghai International Conference Center May 9-13, 2011, Shanghai, China A Decentralized Approach to Multi-agent Planning in the Presence of

More information

Grundlagen der Künstlichen Intelligenz

Grundlagen 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 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

Partially Observable Markov Decision Processes (POMDPs)

Partially Observable Markov Decision Processes (POMDPs) Partially Observable Markov Decision Processes (POMDPs) Sachin Patil Guest Lecture: CS287 Advanced Robotics Slides adapted from Pieter Abbeel, Alex Lee Outline Introduction to POMDPs Locally Optimal Solutions

More information

Bayesian Congestion Control over a Markovian Network Bandwidth Process

Bayesian Congestion Control over a Markovian Network Bandwidth Process Bayesian Congestion Control over a Markovian Network Bandwidth Process Parisa Mansourifard 1/30 Bayesian Congestion Control over a Markovian Network Bandwidth Process Parisa Mansourifard (USC) Joint work

More information

COMP3702/7702 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 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 information

An Introduction to Markov Decision Processes. MDP Tutorial - 1

An Introduction to Markov Decision Processes. MDP Tutorial - 1 An Introduction to Markov Decision Processes Bob Givan Purdue University Ron Parr Duke University MDP Tutorial - 1 Outline Markov Decision Processes defined (Bob) Objective functions Policies Finding Optimal

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

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

Pruning for Monte Carlo Distributed Reinforcement Learning in Decentralized POMDPs

Pruning for Monte Carlo Distributed Reinforcement Learning in Decentralized POMDPs Pruning for Monte Carlo Distributed Reinforcement Learning in Decentralized POMDPs Bikramjit Banerjee School of Computing The University of Southern Mississippi Hattiesburg, MS 39402 Bikramjit.Banerjee@usm.edu

More information

Learning in Zero-Sum Team Markov Games using Factored Value Functions

Learning in Zero-Sum Team Markov Games using Factored Value Functions Learning in Zero-Sum Team Markov Games using Factored Value Functions Michail G. Lagoudakis Department of Computer Science Duke University Durham, NC 27708 mgl@cs.duke.edu Ronald Parr Department of Computer

More information

A Review of the E 3 Algorithm: Near-Optimal Reinforcement Learning in Polynomial Time

A Review of the E 3 Algorithm: Near-Optimal Reinforcement Learning in Polynomial Time A Review of the E 3 Algorithm: Near-Optimal Reinforcement Learning in Polynomial Time April 16, 2016 Abstract In this exposition we study the E 3 algorithm proposed by Kearns and Singh for reinforcement

More information

CS 7180: Behavioral Modeling and Decisionmaking

CS 7180: Behavioral Modeling and Decisionmaking CS 7180: Behavioral Modeling and Decisionmaking in AI Markov Decision Processes for Complex Decisionmaking Prof. Amy Sliva October 17, 2012 Decisions are nondeterministic In many situations, behavior and

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

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

Open Theoretical Questions in Reinforcement Learning

Open Theoretical Questions in Reinforcement Learning Open Theoretical Questions in Reinforcement Learning Richard S. Sutton AT&T Labs, Florham Park, NJ 07932, USA, sutton@research.att.com, www.cs.umass.edu/~rich Reinforcement learning (RL) concerns the problem

More information

Q-learning. Tambet Matiisen

Q-learning. Tambet Matiisen Q-learning Tambet Matiisen (based on chapter 11.3 of online book Artificial Intelligence, foundations of computational agents by David Poole and Alan Mackworth) Stochastic gradient descent Experience

More information

Reinforcement Learning. Yishay Mansour Tel-Aviv University

Reinforcement 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 information

A reinforcement learning scheme for a multi-agent card game with Monte Carlo state estimation

A reinforcement learning scheme for a multi-agent card game with Monte Carlo state estimation A reinforcement learning scheme for a multi-agent card game with Monte Carlo state estimation Hajime Fujita and Shin Ishii, Nara Institute of Science and Technology 8916 5 Takayama, Ikoma, 630 0192 JAPAN

More information

ELEC-E8119 Robotics: Manipulation, Decision Making and Learning Policy gradient approaches. Ville Kyrki

ELEC-E8119 Robotics: Manipulation, Decision Making and Learning Policy gradient approaches. Ville Kyrki ELEC-E8119 Robotics: Manipulation, Decision Making and Learning Policy gradient approaches Ville Kyrki 9.10.2017 Today Direct policy learning via policy gradient. Learning goals Understand basis and limitations

More 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

arxiv: v2 [cs.ai] 20 Dec 2014

arxiv: v2 [cs.ai] 20 Dec 2014 Scalable Planning and Learning for Multiagent POMDPs: Extended Version arxiv:1404.1140v2 [cs.ai] 20 Dec 2014 Christopher Amato CSAIL, MIT Cambridge, MA 02139 camato@csail.mit.edu Frans A. Oliehoek Informatics

More information

15-780: Graduate Artificial Intelligence. Reinforcement learning (RL)

15-780: Graduate Artificial Intelligence. Reinforcement learning (RL) 15-780: Graduate Artificial Intelligence Reinforcement learning (RL) From MDPs to RL We still use the same Markov model with rewards and actions But there are a few differences: 1. We do not assume we

More information

Efficient Maximization in Solving POMDPs

Efficient Maximization in Solving POMDPs Efficient Maximization in Solving POMDPs Zhengzhu Feng Computer Science Department University of Massachusetts Amherst, MA 01003 fengzz@cs.umass.edu Shlomo Zilberstein Computer Science Department University

More information

Lecture 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 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 information

Lecture 10 - Planning under Uncertainty (III)

Lecture 10 - Planning under Uncertainty (III) Lecture 10 - Planning under Uncertainty (III) Jesse Hoey School of Computer Science University of Waterloo March 27, 2018 Readings: Poole & Mackworth (2nd ed.)chapter 12.1,12.3-12.9 1/ 34 Reinforcement

More 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

Balancing 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 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 information

Information Gathering and Reward Exploitation of Subgoals for P

Information Gathering and Reward Exploitation of Subgoals for P Information Gathering and Reward Exploitation of Subgoals for POMDPs Hang Ma and Joelle Pineau McGill University AAAI January 27, 2015 http://www.cs.washington.edu/ai/mobile_robotics/mcl/animations/global-floor.gif

More information

Learning for Multiagent Decentralized Control in Large Partially Observable Stochastic Environments

Learning for Multiagent Decentralized Control in Large Partially Observable Stochastic Environments Learning for Multiagent Decentralized Control in Large Partially Observable Stochastic Environments Miao Liu Laboratory for Information and Decision Systems Cambridge, MA 02139 miaoliu@mit.edu Christopher

More information

Complexity of stochastic branch and bound methods for belief tree search in Bayesian reinforcement learning

Complexity of stochastic branch and bound methods for belief tree search in Bayesian reinforcement learning Complexity of stochastic branch and bound methods for belief tree search in Bayesian reinforcement learning Christos Dimitrakakis Informatics Institute, University of Amsterdam, Amsterdam, The Netherlands

More information

Evaluation of multi armed bandit algorithms and empirical algorithm

Evaluation of multi armed bandit algorithms and empirical algorithm Acta Technica 62, No. 2B/2017, 639 656 c 2017 Institute of Thermomechanics CAS, v.v.i. Evaluation of multi armed bandit algorithms and empirical algorithm Zhang Hong 2,3, Cao Xiushan 1, Pu Qiumei 1,4 Abstract.

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

Optimizing Memory-Bounded Controllers for Decentralized POMDPs

Optimizing Memory-Bounded Controllers for Decentralized POMDPs Optimizing Memory-Bounded Controllers for Decentralized POMDPs Christopher Amato, Daniel S. Bernstein and Shlomo Zilberstein Department of Computer Science University of Massachusetts Amherst, MA 01003

More information

Final. Introduction to Artificial Intelligence. CS 188 Spring You have approximately 2 hours and 50 minutes.

Final. Introduction to Artificial Intelligence. CS 188 Spring You have approximately 2 hours and 50 minutes. CS 188 Spring 2014 Introduction to Artificial Intelligence Final You have approximately 2 hours and 50 minutes. The exam is closed book, closed notes except your two-page crib sheet. Mark your answers

More information

Machine Learning and Bayesian Inference. Unsupervised learning. Can we find regularity in data without the aid of labels?

Machine Learning and Bayesian Inference. Unsupervised learning. Can we find regularity in data without the aid of labels? Machine Learning and Bayesian Inference Dr Sean Holden Computer Laboratory, Room FC6 Telephone extension 6372 Email: sbh11@cl.cam.ac.uk www.cl.cam.ac.uk/ sbh11/ Unsupervised learning Can we find regularity

More information

CMU Lecture 12: Reinforcement Learning. Teacher: Gianni A. Di Caro

CMU 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 information

Reinforcement Learning and Control

Reinforcement 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 information

Lecture 3: Markov Decision Processes

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 information

Distributed Optimization. Song Chong EE, KAIST

Distributed 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 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

Today s s Lecture. Applicability of Neural Networks. Back-propagation. Review of Neural Networks. Lecture 20: Learning -4. Markov-Decision Processes

Today s s Lecture. Applicability of Neural Networks. Back-propagation. Review of Neural Networks. Lecture 20: Learning -4. Markov-Decision Processes Today s s Lecture Lecture 20: Learning -4 Review of Neural Networks Markov-Decision Processes Victor Lesser CMPSCI 683 Fall 2004 Reinforcement learning 2 Back-propagation Applicability of Neural Networks

More information

CS 4649/7649 Robot Intelligence: Planning

CS 4649/7649 Robot Intelligence: Planning CS 4649/7649 Robot Intelligence: Planning Probability Primer Sungmoon Joo School of Interactive Computing College of Computing Georgia Institute of Technology S. Joo (sungmoon.joo@cc.gatech.edu) 1 *Slides

More information

Deep Reinforcement Learning. STAT946 Deep Learning Guest Lecture by Pascal Poupart University of Waterloo October 19, 2017

Deep Reinforcement Learning. STAT946 Deep Learning Guest Lecture by Pascal Poupart University of Waterloo October 19, 2017 Deep Reinforcement Learning STAT946 Deep Learning Guest Lecture by Pascal Poupart University of Waterloo October 19, 2017 Outline Introduction to Reinforcement Learning AlphaGo (Deep RL for Computer Go)

More information

Decentralized Decision Making!

Decentralized Decision Making! Decentralized Decision Making! in Partially Observable, Uncertain Worlds Shlomo Zilberstein Department of Computer Science University of Massachusetts Amherst Joint work with Martin Allen, Christopher

More information

Bayesian Congestion Control over a Markovian Network Bandwidth Process: A multiperiod Newsvendor Problem

Bayesian Congestion Control over a Markovian Network Bandwidth Process: A multiperiod Newsvendor Problem Bayesian Congestion Control over a Markovian Network Bandwidth Process: A multiperiod Newsvendor Problem Parisa Mansourifard 1/37 Bayesian Congestion Control over a Markovian Network Bandwidth Process:

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

Today s Outline. Recap: MDPs. Bellman Equations. Q-Value Iteration. Bellman Backup 5/7/2012. CSE 473: Artificial Intelligence Reinforcement Learning

Today s Outline. Recap: MDPs. Bellman Equations. Q-Value Iteration. Bellman Backup 5/7/2012. CSE 473: Artificial Intelligence Reinforcement Learning CSE 473: Artificial Intelligence Reinforcement Learning Dan Weld Today s Outline Reinforcement Learning Q-value iteration Q-learning Exploration / exploitation Linear function approximation Many slides

More information

Autonomous Helicopter Flight via Reinforcement Learning

Autonomous Helicopter Flight via Reinforcement Learning Autonomous Helicopter Flight via Reinforcement Learning Authors: Andrew Y. Ng, H. Jin Kim, Michael I. Jordan, Shankar Sastry Presenters: Shiv Ballianda, Jerrolyn Hebert, Shuiwang Ji, Kenley Malveaux, Huy

More information

RL 14: POMDPs continued

RL 14: POMDPs continued RL 14: POMDPs continued Michael Herrmann University of Edinburgh, School of Informatics 06/03/2015 POMDPs: Points to remember Belief states are probability distributions over states Even if computationally

More information

A Model of Human Capital Accumulation and Occupational Choices. A simplified version of Keane and Wolpin (JPE, 1997)

A Model of Human Capital Accumulation and Occupational Choices. A simplified version of Keane and Wolpin (JPE, 1997) A Model of Human Capital Accumulation and Occupational Choices A simplified version of Keane and Wolpin (JPE, 1997) We have here three, mutually exclusive decisions in each period: 1. Attend school. 2.

More information

Motivation for introducing probabilities

Motivation 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 information

Reinforcement Learning Active Learning

Reinforcement Learning Active Learning Reinforcement Learning Active Learning Alan Fern * Based in part on slides by Daniel Weld 1 Active Reinforcement Learning So far, we ve assumed agent has a policy We just learned how good it is Now, suppose

More information

Reinforcement Learning. Introduction

Reinforcement 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 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

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

Individual Planning in Infinite-Horizon Multiagent Settings: Inference, Structure and Scalability

Individual Planning in Infinite-Horizon Multiagent Settings: Inference, Structure and Scalability Individual Planning in Infinite-Horizon Multiagent Settings: Inference, Structure and Scalability Xia Qu Epic Systems Verona, WI 53593 quxiapisces@gmail.com Prashant Doshi THINC Lab, Dept. of Computer

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

ARTIFICIAL INTELLIGENCE. Reinforcement learning

ARTIFICIAL INTELLIGENCE. Reinforcement learning INFOB2KI 2018-2019 Utrecht University The Netherlands ARTIFICIAL INTELLIGENCE Reinforcement learning Lecturer: Silja Renooij These slides are part of the INFOB2KI Course Notes available from www.cs.uu.nl/docs/vakken/b2ki/schema.html

More information

Sample Bounded Distributed Reinforcement Learning for Decentralized POMDPs

Sample Bounded Distributed Reinforcement Learning for Decentralized POMDPs Proceedings of the Twenty-Sixth AAAI Conference on Artificial Intelligence Sample Bounded Distributed Reinforcement Learning for Decentralized POMDPs Bikramjit Banerjee 1, Jeremy Lyle 2, Landon Kraemer

More information

Minimizing Communication Cost in a Distributed Bayesian Network Using a Decentralized MDP

Minimizing Communication Cost in a Distributed Bayesian Network Using a Decentralized MDP Minimizing Communication Cost in a Distributed Bayesian Network Using a Decentralized MDP Jiaying Shen Department of Computer Science University of Massachusetts Amherst, MA 0003-460, USA jyshen@cs.umass.edu

More information

Artificial Intelligence & Sequential Decision Problems

Artificial 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 information

Bayesian reinforcement learning and partially observable Markov decision processes November 6, / 24

Bayesian reinforcement learning and partially observable Markov decision processes November 6, / 24 and partially observable Markov decision processes Christos Dimitrakakis EPFL November 6, 2013 Bayesian reinforcement learning and partially observable Markov decision processes November 6, 2013 1 / 24

More information

Reinforcement Learning

Reinforcement Learning Reinforcement Learning Cyber Rodent Project Some slides from: David Silver, Radford Neal CSC411: Machine Learning and Data Mining, Winter 2017 Michael Guerzhoy 1 Reinforcement Learning Supervised learning:

More 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

European Workshop on Reinforcement Learning A POMDP Tutorial. Joelle Pineau. McGill University

European Workshop on Reinforcement Learning A POMDP Tutorial. Joelle Pineau. McGill University European Workshop on Reinforcement Learning 2013 A POMDP Tutorial Joelle Pineau McGill University (With many slides & pictures from Mauricio Araya-Lopez and others.) August 2013 Sequential decision-making

More information

Multiagent (Deep) Reinforcement Learning

Multiagent (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 information

Bayesian Active Learning With Basis Functions

Bayesian Active Learning With Basis Functions Bayesian Active Learning With Basis Functions Ilya O. Ryzhov Warren B. Powell Operations Research and Financial Engineering Princeton University Princeton, NJ 08544, USA IEEE ADPRL April 13, 2011 1 / 29

More information

16.410/413 Principles of Autonomy and Decision Making

16.410/413 Principles of Autonomy and Decision Making 16.410/413 Principles of Autonomy and Decision Making Lecture 23: Markov Decision Processes Policy Iteration Emilio Frazzoli Aeronautics and Astronautics Massachusetts Institute of Technology December

More information

Outline. CSE 573: Artificial Intelligence Autumn Agent. Partial Observability. Markov Decision Process (MDP) 10/31/2012

Outline. CSE 573: Artificial Intelligence Autumn Agent. Partial Observability. Markov Decision Process (MDP) 10/31/2012 CSE 573: Artificial Intelligence Autumn 2012 Reasoning about Uncertainty & Hidden Markov Models Daniel Weld Many slides adapted from Dan Klein, Stuart Russell, Andrew Moore & Luke Zettlemoyer 1 Outline

More information

16.4 Multiattribute Utility Functions

16.4 Multiattribute Utility Functions 285 Normalized utilities The scale of utilities reaches from the best possible prize u to the worst possible catastrophe u Normalized utilities use a scale with u = 0 and u = 1 Utilities of intermediate

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

1 MDP Value Iteration Algorithm

1 MDP Value Iteration Algorithm CS 0. - Active Learning Problem Set Handed out: 4 Jan 009 Due: 9 Jan 009 MDP Value Iteration Algorithm. Implement the value iteration algorithm given in the lecture. That is, solve Bellman s equation using

More information

Lecture 25: Learning 4. Victor R. Lesser. CMPSCI 683 Fall 2010

Lecture 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 information

CS 234 Midterm - Winter

CS 234 Midterm - Winter CS 234 Midterm - Winter 2017-18 **Do not turn this page until you are instructed to do so. Instructions Please answer the following questions to the best of your ability. Read all the questions first before

More information

Reinforcement Learning

Reinforcement 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 information

Exploration. 2015/10/12 John Schulman

Exploration. 2015/10/12 John Schulman Exploration 2015/10/12 John Schulman What is the exploration problem? Given a long-lived agent (or long-running learning algorithm), how to balance exploration and exploitation to maximize long-term rewards

More information

Reinforcement learning

Reinforcement learning Reinforcement learning Based on [Kaelbling et al., 1996, Bertsekas, 2000] Bert Kappen Reinforcement learning Reinforcement learning is the problem faced by an agent that must learn behavior through trial-and-error

More information

Preference Elicitation for Sequential Decision Problems

Preference Elicitation for Sequential Decision Problems Preference Elicitation for Sequential Decision Problems Kevin Regan University of Toronto Introduction 2 Motivation Focus: Computational approaches to sequential decision making under uncertainty These

More information

Decayed Markov Chain Monte Carlo for Interactive POMDPs

Decayed Markov Chain Monte Carlo for Interactive POMDPs Decayed Markov Chain Monte Carlo for Interactive POMDPs Yanlin Han Piotr Gmytrasiewicz Department of Computer Science University of Illinois at Chicago Chicago, IL 60607 {yhan37,piotr}@uic.edu Abstract

More information

Low-Regret for Online Decision-Making

Low-Regret for Online Decision-Making Siddhartha Banerjee and Alberto Vera November 6, 2018 1/17 Introduction Compensated Coupling Bayes Selector Conclusion Motivation 2/17 Introduction Compensated Coupling Bayes Selector Conclusion Motivation

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 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 information

Machine Learning I Reinforcement Learning

Machine 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 information

Food delivered. Food obtained S 3

Food delivered. Food obtained S 3 Press lever Enter magazine * S 0 Initial state S 1 Food delivered * S 2 No reward S 2 No reward S 3 Food obtained Supplementary Figure 1 Value propagation in tree search, after 50 steps of learning the

More information

Approximate Universal Artificial Intelligence

Approximate Universal Artificial Intelligence Approximate Universal Artificial Intelligence A Monte-Carlo AIXI Approximation Joel Veness Kee Siong Ng Marcus Hutter David Silver University of New South Wales National ICT Australia The Australian National

More information

Bayes-Adaptive POMDPs: Toward an Optimal Policy for Learning POMDPs with Parameter Uncertainty

Bayes-Adaptive POMDPs: Toward an Optimal Policy for Learning POMDPs with Parameter Uncertainty Bayes-Adaptive POMDPs: Toward an Optimal Policy for Learning POMDPs with Parameter Uncertainty Stéphane Ross School of Computer Science McGill University, Montreal (Qc), Canada, H3A 2A7 stephane.ross@mail.mcgill.ca

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

The exam is closed book, closed calculator, and closed notes except your one-page crib sheet.

The exam is closed book, closed calculator, and closed notes except your one-page crib sheet. CS 188 Fall 2018 Introduction to Artificial Intelligence Practice Final You have approximately 2 hours 50 minutes. The exam is closed book, closed calculator, and closed notes except your one-page crib

More information