Point-Based Value Iteration for Constrained POMDPs

Size: px
Start display at page:

Download "Point-Based Value Iteration for Constrained POMDPs"

Transcription

1 Point-Based Value Iteration for Constrained POMDPs Dongho Kim Jaesong Lee Kee-Eung Kim Department of Computer Science Pascal Poupart School of Computer Science IJCAI

2 Motivation goals Agent action oservation Environment Partially oservale Markov decision processes (POMDPs) [Kaelling98] Modeling sequential decision making under partial or uncertain oservations Single reward function encodes the immediate utility of executing actions. Required to manually alance different ojectives into the single reward function Constrained POMDPs (CPOMDPs) Prolems with limited resource or multiple ojectives Maximizing one ojective (reward) while constraining other ojectives (costs) CPOMDP has not received as much attention as CMDPs. [Altman99] Exception: DP method for finding deterministic policies [Isom08] Dongho Kim 2

3 Motivation Resource-limited agent, e.g., attery-equipped root Accomplish as many goals as possile given a finite amount of energy Spoken dialogue system [Williams07] e.g., minimize length of dialogue while guaranteeing 95% dialogue success rate Reward : -1 for each dialogue turn Cost : +1 for each unsuccessful dialogue, 0 for each successful dialogue Dialogue : s 0 s 1 s 2 s T R = 1 C = 0 R = 1 C = 0 R = 1 C = 0 R = 1 C = +1 for unsuccessful dialogue C = 0 for successful dialogue Goal: maximize E γ t t r t s.t. E γ t t c t c We propose exact and approximate methods for solving CPOMDPs. Dongho Kim 3

4 Suoptimality of deterministic policies in CPOMDPs lazy, p = 0.9 R = 0, C = 0 lazy R = 0, C = 0 AdvisorHappy lazy, p = 0.1 R = 0, C = 0 AdvisorAngry Procrastinating student prolem work R = 1 C = 1 Optimal deterministic policy At t = 0, lazy At t = 1, work value = 0.9γ, cumulative cost = γ Optimal randomized policy At t = 0, work with pro. of c and lazy with pro. of 1 c At t 1, lazy JoDone work R = 0 C = 1 value = c, cumulative cost = c with pro. of c 0 = 1,0,0 γ < c < 1 Reward and cost for work at each timestep t elief reward cost 0 [1,0,0] [0.9,0.1,0] 0.9γ γ 2 [0.81,0.19,0] 0.81γ 2 γ 2 Dongho Kim 4

5 Value iteration in CPOMDPs Value function of CPOMDPs is a set of α-vector pairs value α 2,r α 3,r α 1,r cumulative cost α 2,c α 3,c α 1,c c V = α i,r, α i,c i α i,r and α i,c are i-th vectors for cumulative reward and cost respectively. Exact DP update via enumeration α i,r (s) = R(s, a)/ Z + γ T s, a, s O s s S, a, z α i,r a i,c (s) = C(s, a)/ Z + γ T s, a, s O s s S, a, z α i,c V = a A z Z α i,r, α i,c i, Creates exponentially many α-vector pairs V = A V Z Pruning is needed s s Dongho Kim 5

6 Exact DP update for CPOMDPs Pruning y mixed integer linear program (MILP) [Isom08] Check whether α r, α c is dominated y V = α i,r, α i,c i Not dominated at : cost c and higher value than other vectors with cost c value α 1,r α 2,r α r If there exists where α r, α c is not dominated, it will not e pruned. Shortcomings in MILP pruning Considers only deterministic policies cost α 1,c α 2,c Need to consider randomized policies (convex comination of α-vectors) Prunes α-vector pairs violating the cost constraint in each DP update Satisfying the cost constraint does not necessarily mean that the constraint should e satisfied at every time step. α c c Boolean variales MILP cost α c c Dongho Kim 6

7 Exact DP update for CPOMDPs Pruning y minimax quadratically constrained program (QCP) Inner maximization: Is α r, α c dominated at? Outer mininization: Where is α r, α c not dominated? Not dominated at : no convex comination with higher value and same or lower cost Inner maximization: for fixed Find convex comination which dominates α r, α c y maximizing the gap If the gap is positive, α r, α c is dominated at Outer minimization value α r α 1,r α 2,r gap = value of convex comination - value of α r cost α 1,c α c α 2,c Find where α r, α c is not dominated y minimizing the gap If the gap is negative at the resulting, α r, α c will not e pruned. Dongho Kim 7

8 Point-ased DP for CPOMDPs value Point-ased value iteration (PBVI) for standard POMDPs[Pineau06] Maintains the est α-vector for each B = 0, 1,, q Adapting standard PBVI to CPOMDPs in a simple way Enumerates α-vector pairs and performs pruning confined to B Minimax QCP pruning ecomes LP for each B find a randomized policy which dominates α r, α c at value α r α 1,r cost α 1,c α c α 2,r α 2,c Still many α-vectors at each B No information on costs at B Dongho Kim 8

9 Admissile cost [Piunovskiy00] Admissile cost is Expected cumulative cost that can e additionally incurred in the future s 0 s 1 s t s t+1 c 0 s t+2 γc 1 γ t c t γ t+1 c t+1 γ t+2 c t+2 Expected cumulative cost up to t W t = γ τ c τ t τ=0 Admissile cost at t + 1 d t+1 = 1 γ t+1 (c W t ) d t d t+1 Recursive formulation: d t+1 = 1 γ d t c t Dongho Kim 9

10 PBVI with admissile cost for CPOMDPs Samples elief-admissile cost pairs B = 0, d 0, 1, d 1,, q, d q Maintains the est randomized policy for each, d B Using LP for finding the est convex comination for, d value α 1,r α 3,r α 2,r Point-ased DP update For each, d cost α 1,c α 2,c B, find the est rand. policy at (τ, a, z, d z ) for each a, z Heuristic: distriuting admissile cost in proportion to the oservation proaility, i.e., d z = 1 d C, a P(z, a) γ α 3,c d LP solution: Convex comination of at most 2 α-vector pairs value cost At most 2 B α-vector pairs d 0 d Dongho Kim 10

11 Experiment: Quickest change detection Quickest change detection[isom08] Minimize detection delay while constraining the proaility of false alarm S = 3, A = 2, Z = 3 MILP (det) vs. QCP (rand) vs. PBVI (rand) MILP and QCP could not perform DP updates more than 6 and 5 timesteps. PBVI scaled effectively more than 10 timesteps. PBVI performed close to exact methods. NoAlarm, p = 0.99 R = 0, C = 0 NoAlarm p = 0.01 R = 0, C = 0 NoAlarm R = 1, C = 0 Alarm R = 0, C = 0 PreChange PostChange PostAlarm Alarm false alarm R = 0, C = 1 Dongho Kim 11

12 Experiment: n-city ticketing prolem n-city ticketing prolem[williams07] Figure out the origin and the destination among n-cities Sumit the ticket purchase request once it has gathered sufficient information Due to the speech recognition errors, the oserved user s response can e different from the true response -1 reward for each timestep, 1 cost for a wrong ticket PBVI result for n = 3, P e = 0.2 S = 1945, A = 16, Z = 18 More dialogue turns for smaller c Needs more information gathering steps to e more accurate Dongho Kim 12

13 Conclusion We showed that optimal policies in CPOMDPs can e randomized We presented exact and approximate methods for CPOMDPs Exact method with minimax QCP pruning Approximate method ased on PBVI Can extend to multiple constraints and different discount factor for each cost function Future work Adopting state-of-the-art POMDP solvers with heuristic elief exploration Extension to average reward and cost criterion Extension to factored CPOMDPs Dongho Kim 13

14 Reference [Altman99] E. Altman. Constrained Markov Decision Processes. Chapman & Hall/CRC, [Isom08] J. D. Isom, S. P. Meyn, and R. D. Braatz. Piecewise linear dynamic programming for constrained POMDPs. In Proc. of AAAI, [Kaelling98] L. P. Kaelling, M. L. Littman, and A. R. Cassandra. Planning and acting in partially oservale stochastic domains. Artificial Intelligence, 101:99-134, [Pineau06] J. Pineau, G. Gordon, and S. Thrun. Anytime point-ased approximations for large POMDPs. JAIR, 27: , [Piunovskiy00] A. B. Piunovskiy and X. Mao. Constrained Markovian decision processes: the dynamic programming approach. Operations Research Letters, 27(3): , [Williams07] J. D. Willians and S. Young. Partially oservale Markov decision processes for spoken dialog systems. Computer Speech and Language, 21(2): , Dongho Kim 14

Piecewise Linear Dynamic Programming for Constrained POMDPs

Piecewise Linear Dynamic Programming for Constrained POMDPs Proceedings of the Twenty-Third AAAI Conference on Artificial Intelligence (28) Piecewise Linear Dynamic Programming for Constrained POMDPs Joshua D. Isom Sikorsky Aircraft Corporation Stratford, CT 6615

More information

CAP Plan, Activity, and Intent Recognition

CAP Plan, Activity, and Intent Recognition CAP6938-02 Plan, Activity, and Intent Recognition Lecture 10: Sequential Decision-Making Under Uncertainty (part 1) MDPs and POMDPs Instructor: Dr. Gita Sukthankar Email: gitars@eecs.ucf.edu SP2-1 Reminder

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

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

Solving Risk-Sensitive POMDPs with and without Cost Observations

Solving Risk-Sensitive POMDPs with and without Cost Observations Solving Risk-Sensitive POMDPs with and without Cost Observations Ping Hou Department of Computer Science New Mexico State University Las Cruces, NM 88003, USA phou@cs.nmsu.edu William Yeoh Department of

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

Partially Observable Markov Decision Processes (POMDPs)

Partially Observable Markov Decision Processes (POMDPs) Partially Observable Markov Decision Processes (POMDPs) Geoff Hollinger Sequential Decision Making in Robotics Spring, 2011 *Some media from Reid Simmons, Trey Smith, Tony Cassandra, Michael Littman, and

More information

Symbolic Dynamic Programming for Continuous State and Observation POMDPs

Symbolic Dynamic Programming for Continuous State and Observation POMDPs Symbolic Dynamic Programming for Continuous State and Observation POMDPs Zahra Zamani ANU & NICTA Canberra, Australia zahra.zamani@anu.edu.au Pascal Poupart U. of Waterloo Waterloo, Canada ppoupart@uwaterloo.ca

More information

Symbolic Dynamic Programming for Continuous State and Observation POMDPs

Symbolic Dynamic Programming for Continuous State and Observation POMDPs Symbolic Dynamic Programming for Continuous State and Observation POMDPs Zahra Zamani ANU & NICTA Canberra, Australia zahra.zamani@anu.edu.au Pascal Poupart U. of Waterloo Waterloo, Canada ppoupart@uwaterloo.ca

More information

SPOKEN dialog systems (SDSs) help people accomplish

SPOKEN dialog systems (SDSs) help people accomplish IEEE TRANS. ON AUDIO, SPEECH & LANGUAGE PROCESSING, VOL.???, NO.???, MONTH??? YEAR??? 1 Scaling POMDPs for spoken dialog management Astract Control in spoken dialog systems is challenging largely ecause

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

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

Towards Faster Planning with Continuous Resources in Stochastic Domains

Towards Faster Planning with Continuous Resources in Stochastic Domains Towards Faster Planning with Continuous Resources in Stochastic Domains Janusz Marecki and Milind Tambe Computer Science Department University of Southern California 941 W 37th Place, Los Angeles, CA 989

More information

Kalman Based Temporal Difference Neural Network for Policy Generation under Uncertainty (KBTDNN)

Kalman Based Temporal Difference Neural Network for Policy Generation under Uncertainty (KBTDNN) Kalman Based Temporal Difference Neural Network for Policy Generation under Uncertainty (KBTDNN) Alp Sardag and H.Levent Akin Bogazici University Department of Computer Engineering 34342 Bebek, Istanbul,

More information

Scaling up Partially Observable Markov Decision Processes for Dialogue Management

Scaling up Partially Observable Markov Decision Processes for Dialogue Management Scaling up Partially Observable Markov Decision Processes for Dialogue Management Jason D. Williams 22 July 2005 Machine Intelligence Laboratory Cambridge University Engineering Department Outline Dialogue

More information

Robust Policy Computation in Reward-uncertain MDPs using Nondominated Policies

Robust Policy Computation in Reward-uncertain MDPs using Nondominated Policies Robust Policy Computation in Reward-uncertain MDPs using Nondominated Policies Kevin Regan University of Toronto Toronto, Ontario, Canada, M5S 3G4 kmregan@cs.toronto.edu Craig Boutilier University of Toronto

More information

Constrained Bayesian Reinforcement Learning via Approximate Linear Programming

Constrained Bayesian Reinforcement Learning via Approximate Linear Programming Constrained Bayesian Reinforcement Learning via Approximate Linear Programming Jongmin Lee, Youngsoo Jang, Pascal Poupart, Kee-Eung Kim School of Computing, KAIST, Republic of Korea David R. Cheriton School

More information

Finite-State Controllers Based on Mealy Machines for Centralized and Decentralized POMDPs

Finite-State Controllers Based on Mealy Machines for Centralized and Decentralized POMDPs Finite-State Controllers Based on Mealy Machines for Centralized and Decentralized POMDPs Christopher Amato Department of Computer Science University of Massachusetts Amherst, MA 01003 USA camato@cs.umass.edu

More information

Prediction-Constrained POMDPs

Prediction-Constrained POMDPs Prediction-Constrained POMDPs Joseph Futoma Harvard SEAS Michael C. Hughes Dept of. Computer Science, Tufts University Abstract Finale Doshi-Velez Harvard SEAS We propose prediction-constrained (PC) training

More information

Heuristic Search Value Iteration for POMDPs

Heuristic Search Value Iteration for POMDPs 520 SMITH & SIMMONS UAI 2004 Heuristic Search Value Iteration for POMDPs Trey Smith and Reid Simmons Robotics Institute, Carnegie Mellon University {trey,reids}@ri.cmu.edu Abstract We present a novel POMDP

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

Region-Based Dynamic Programming for Partially Observable Markov Decision Processes

Region-Based Dynamic Programming for Partially Observable Markov Decision Processes Region-Based Dynamic Programming for Partially Observable Markov Decision Processes Zhengzhu Feng Department of Computer Science University of Massachusetts Amherst, MA 01003 fengzz@cs.umass.edu Abstract

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

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

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

Section Notes 9. Midterm 2 Review. Applied Math / Engineering Sciences 121. Week of December 3, 2018

Section Notes 9. Midterm 2 Review. Applied Math / Engineering Sciences 121. Week of December 3, 2018 Section Notes 9 Midterm 2 Review Applied Math / Engineering Sciences 121 Week of December 3, 2018 The following list of topics is an overview of the material that was covered in the lectures and sections

More information

An Adaptive Clustering Method for Model-free Reinforcement Learning

An 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 information

CS788 Dialogue Management Systems Lecture #2: Markov Decision Processes

CS788 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 information

Online Partial Conditional Plan Synthesis for POMDPs with Safe-Reachability Objectives

Online Partial Conditional Plan Synthesis for POMDPs with Safe-Reachability Objectives To appear in the proceedings of the 13th International Workshop on the Algorithmic Foundations of Robotics (WAFR), 2018 Online Partial Conditional Plan Synthesis for POMDPs with Safe-Reachability Objectives

More information

Planning and Acting in Partially Observable Stochastic Domains

Planning and Acting in Partially Observable Stochastic Domains Planning and Acting in Partially Observable Stochastic Domains Leslie Pack Kaelbling*, Michael L. Littman**, Anthony R. Cassandra*** *Computer Science Department, Brown University, Providence, RI, USA

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

Dialogue as a Decision Making Process

Dialogue as a Decision Making Process Dialogue as a Decision Making Process Nicholas Roy Challenges of Autonomy in the Real World Wide range of sensors Noisy sensors World dynamics Adaptability Incomplete information Robustness under uncertainty

More information

Lecture 18: Reinforcement Learning Sanjeev Arora Elad Hazan

Lecture 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 information

Reinforcement Learning for Continuous. Action using Stochastic Gradient Ascent. Hajime KIMURA, Shigenobu KOBAYASHI JAPAN

Reinforcement Learning for Continuous. Action using Stochastic Gradient Ascent. Hajime KIMURA, Shigenobu KOBAYASHI JAPAN Reinforcement Learning for Continuous Action using Stochastic Gradient Ascent Hajime KIMURA, Shigenobu KOBAYASHI Tokyo Institute of Technology, 4259 Nagatsuda, Midori-ku Yokohama 226-852 JAPAN Abstract:

More information

Christopher Watkins and Peter Dayan. Noga Zaslavsky. The Hebrew University of Jerusalem Advanced Seminar in Deep Learning (67679) November 1, 2015

Christopher 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 information

Dialogue management: Parametric approaches to policy optimisation. Dialogue Systems Group, Cambridge University Engineering Department

Dialogue management: Parametric approaches to policy optimisation. Dialogue Systems Group, Cambridge University Engineering Department Dialogue management: Parametric approaches to policy optimisation Milica Gašić Dialogue Systems Group, Cambridge University Engineering Department 1 / 30 Dialogue optimisation as a reinforcement learning

More information

Inverse Reinforcement Learning in Partially Observable Environments

Inverse Reinforcement Learning in Partially Observable Environments Proceedings of the Twenty-First International Joint Conference on Artificial Intelligence (IJCAI-09) Inverse Reinforcement Learning in Partially Observable Environments Jaedeug Choi and Kee-Eung Kim Department

More information

Solving Stochastic Planning Problems With Large State and Action Spaces

Solving Stochastic Planning Problems With Large State and Action Spaces Solving Stochastic Planning Problems With Large State and Action Spaces Thomas Dean, Robert Givan, and Kee-Eung Kim Thomas Dean and Kee-Eung Kim Robert Givan Department of Computer Science Department of

More information

Accelerated Vector Pruning for Optimal POMDP Solvers

Accelerated Vector Pruning for Optimal POMDP Solvers Accelerated Vector Pruning for Optimal POMDP Solvers Erwin Walraven and Matthijs T. J. Spaan Delft University of Technology Mekelweg 4, 2628 CD Delft, The Netherlands Abstract Partially Observable Markov

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

Point Based Value Iteration with Optimal Belief Compression for Dec-POMDPs

Point Based Value Iteration with Optimal Belief Compression for Dec-POMDPs Point Based Value Iteration with Optimal Belief Compression for Dec-POMDPs Liam MacDermed College of Computing Georgia Institute of Technology Atlanta, GA 30332 liam@cc.gatech.edu Charles L. Isbell College

More information

CS 4100 // artificial intelligence. Recap/midterm review!

CS 4100 // artificial intelligence. Recap/midterm review! CS 4100 // artificial intelligence instructor: byron wallace Recap/midterm review! Attribution: many of these slides are modified versions of those distributed with the UC Berkeley CS188 materials Thanks

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

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

Topics of Active Research in Reinforcement Learning Relevant to Spoken Dialogue Systems

Topics of Active Research in Reinforcement Learning Relevant to Spoken Dialogue Systems Topics of Active Research in Reinforcement Learning Relevant to Spoken Dialogue Systems Pascal Poupart David R. Cheriton School of Computer Science University of Waterloo 1 Outline Review Markov Models

More information

Planning Under Uncertainty II

Planning Under Uncertainty II Planning Under Uncertainty II Intelligent Robotics 2014/15 Bruno Lacerda Announcement No class next Monday - 17/11/2014 2 Previous Lecture Approach to cope with uncertainty on outcome of actions Markov

More information

Recent Developments in Statistical Dialogue Systems

Recent Developments in Statistical Dialogue Systems Recent Developments in Statistical Dialogue Systems Steve Young Machine Intelligence Laboratory Information Engineering Division Cambridge University Engineering Department Cambridge, UK Contents Review

More information

Relational Partially Observable MDPs

Relational Partially Observable MDPs Proceedings of the Twenty-Fourth AAAI Conference on Artificial Intelligence (AAAI-10) elational Partially Observable MDPs Chenggang Wang and oni Khardon Department of Computer Science Tufts University

More information

Function Approximation for Continuous Constrained MDPs

Function Approximation for Continuous Constrained MDPs Function Approximation for Continuous Constrained MDPs Aditya Undurti, Alborz Geramifard, Jonathan P. How Abstract In this work we apply function approximation techniques to solve continuous, constrained

More information

Exploiting Structure to Efficiently Solve Large Scale Partially Observable Markov Decision Processes. Pascal Poupart

Exploiting Structure to Efficiently Solve Large Scale Partially Observable Markov Decision Processes. Pascal Poupart Exploiting Structure to Efficiently Solve Large Scale Partially Observable Markov Decision Processes by Pascal Poupart A thesis submitted in conformity with the requirements for the degree of Doctor of

More information

PROBABILISTIC PLANNING WITH RISK-SENSITIVE CRITERION PING HOU. A dissertation submitted to the Graduate School

PROBABILISTIC PLANNING WITH RISK-SENSITIVE CRITERION PING HOU. A dissertation submitted to the Graduate School PROBABILISTIC PLANNING WITH RISK-SENSITIVE CRITERION BY PING HOU A dissertation submitted to the Graduate School in partial fulfillment of the requirements for the degree Doctor of Philosophy Major Subject:

More information

2534 Lecture 4: Sequential Decisions and Markov Decision Processes

2534 Lecture 4: Sequential Decisions and Markov Decision Processes 2534 Lecture 4: Sequential Decisions and Markov Decision Processes Briefly: preference elicitation (last week s readings) Utility Elicitation as a Classification Problem. Chajewska, U., L. Getoor, J. Norman,Y.

More information

RAO : an Algorithm for Chance-Constrained POMDP s

RAO : an Algorithm for Chance-Constrained POMDP s RAO : an Algorithm for Chance-Constrained POMDP s Pedro Santana and Sylvie Thiébaux + and Brian Williams Massachusetts Institute of Technology, CSAIL + The Australian National University & NICTA 32 Vassar

More information

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

Markov Decision Processes and Solving Finite Problems. February 8, 2017 Markov Decision Processes and Solving Finite Problems February 8, 2017 Overview of Upcoming Lectures Feb 8: Markov decision processes, value iteration, policy iteration Feb 13: Policy gradients Feb 15:

More information

Solving POMDPs with Continuous or Large Discrete Observation Spaces

Solving POMDPs with Continuous or Large Discrete Observation Spaces Solving POMDPs with Continuous or Large Discrete Observation Spaces Jesse Hoey Department of Computer Science University of Toronto Toronto, ON, M5S 3H5 jhoey@cs.toronto.edu Pascal Poupart School of Computer

More information

Probabilistic robot planning under model uncertainty: an active learning approach

Probabilistic robot planning under model uncertainty: an active learning approach Probabilistic robot planning under model uncertainty: an active learning approach Robin JAULMES, Joelle PINEAU and Doina PRECUP School of Computer Science McGill University Montreal, QC CANADA H3A 2A7

More information

On Prediction and Planning in Partially Observable Markov Decision Processes with Large Observation Sets

On Prediction and Planning in Partially Observable Markov Decision Processes with Large Observation Sets On Prediction and Planning in Partially Observable Markov Decision Processes with Large Observation Sets Pablo Samuel Castro pcastr@cs.mcgill.ca McGill University Joint work with: Doina Precup and Prakash

More information

Nonparametric Bayesian Inverse Reinforcement Learning

Nonparametric Bayesian Inverse Reinforcement Learning PRML Summer School 2013 Nonparametric Bayesian Inverse Reinforcement Learning Jaedeug Choi JDCHOI@AI.KAIST.AC.KR Sequential Decision Making (1) Multiple decisions over time are made to achieve goals Reinforcement

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 2015 Introduction to Artificial Intelligence Final You have approximately 2 hours and 50 minutes. The exam is closed book, closed calculator, and closed notes except your one-page crib sheet.

More information

Symbolic Perseus: a Generic POMDP Algorithm with Application to Dynamic Pricing with Demand Learning

Symbolic Perseus: a Generic POMDP Algorithm with Application to Dynamic Pricing with Demand Learning Symbolic Perseus: a Generic POMDP Algorithm with Application to Dynamic Pricing with Demand Learning Pascal Poupart (University of Waterloo) INFORMS 2009 1 Outline Dynamic Pricing as a POMDP Symbolic Perseus

More information

Discrete planning (an introduction)

Discrete 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 information

Machine Learning for Sustainable Development and Biological Conservation

Machine Learning for Sustainable Development and Biological Conservation Machine Learning for Sustainable Development and Biological Conservation Tom Dietterich Distinguished Professor, Oregon State University President, Association for the Advancement of Artificial Intelligence

More information

Probabilistic Planning. George Konidaris

Probabilistic 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 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

Interactive POMDP Lite: Towards Practical Planning to Predict and Exploit Intentions for Interacting with Self-Interested Agents

Interactive POMDP Lite: Towards Practical Planning to Predict and Exploit Intentions for Interacting with Self-Interested Agents Proceedings of the Twenty-Third International Joint Conference on Artificial Intelligence Interactive POMDP Lite: Towards Practical Planning to Predict and Exploit Intentions for Interacting with Self-Interested

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

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

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

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

Learning in non-stationary Partially Observable Markov Decision Processes

Learning in non-stationary Partially Observable Markov Decision Processes Learning in non-stationary Partially Observable Markov Decision Processes Robin JAULMES, Joelle PINEAU, Doina PRECUP McGill University, School of Computer Science, 3480 University St., Montreal, QC, Canada,

More information

Partially Observable Markov Decision Processes (POMDPs) Pieter Abbeel UC Berkeley EECS

Partially Observable Markov Decision Processes (POMDPs) Pieter Abbeel UC Berkeley EECS Partially Observable Markov Decision Processes (POMDPs) Pieter Abbeel UC Berkeley EECS Many slides adapted from Jur van den Berg Outline POMDPs Separation Principle / Certainty Equivalence Locally Optimal

More information

Bayes-Adaptive POMDPs 1

Bayes-Adaptive POMDPs 1 Bayes-Adaptive POMDPs 1 Stéphane Ross, Brahim Chaib-draa and Joelle Pineau SOCS-TR-007.6 School of Computer Science McGill University Montreal, Qc, Canada Department of Computer Science and Software Engineering

More information

OPTIMALITY OF RANDOMIZED TRUNK RESERVATION FOR A PROBLEM WITH MULTIPLE CONSTRAINTS

OPTIMALITY OF RANDOMIZED TRUNK RESERVATION FOR A PROBLEM WITH MULTIPLE CONSTRAINTS OPTIMALITY OF RANDOMIZED TRUNK RESERVATION FOR A PROBLEM WITH MULTIPLE CONSTRAINTS Xiaofei Fan-Orzechowski Department of Applied Mathematics and Statistics State University of New York at Stony Brook Stony

More information

Artificial Intelligence. Non-deterministic state model. Model for non-deterministic problems. Solutions. Blai Bonet

Artificial Intelligence. Non-deterministic state model. Model for non-deterministic problems. Solutions. Blai Bonet Artificial Intelligence Blai Bonet Non-deterministic state model Universidad Simón Boĺıvar, Caracas, Venezuela Model for non-deterministic problems Solutions State models with non-deterministic actions

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

Course 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 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 information

Symbolic Dynamic Programming for First-order POMDPs

Symbolic Dynamic Programming for First-order POMDPs Symbolic Dynamic Programming for First-order POMDPs Scott Sanner NICTA & ANU Canberra, Australia scott.sanner@nicta.com.au Kristian Kersting Fraunhofer IAIS Sankt Augustin, Germany kristian.kersting@iais.fraunhofer.de

More information

POMDPs and Policy Gradients

POMDPs and Policy Gradients POMDPs and Policy Gradients MLSS 2006, Canberra Douglas Aberdeen Canberra Node, RSISE Building Australian National University 15th February 2006 Outline 1 Introduction What is Reinforcement Learning? Types

More information

REINFORCEMENT LEARNING

REINFORCEMENT LEARNING REINFORCEMENT LEARNING Larry Page: Where s Google going next? DeepMind's DQN playing Breakout Contents Introduction to Reinforcement Learning Deep Q-Learning INTRODUCTION TO REINFORCEMENT LEARNING Contents

More information

Solution Methods for Constrained Markov Decision Process with Continuous Probability Modulation

Solution Methods for Constrained Markov Decision Process with Continuous Probability Modulation Solution Methods for Constrained Markov Decision Process with Continuous Probability Modulation Janusz Marecki, Marek Petrik, Dharmashankar Subramanian Business Analytics and Mathematical Sciences IBM

More information

Multi-Objective Decision Making

Multi-Objective Decision Making Multi-Objective Decision Making Shimon Whiteson & Diederik M. Roijers Department of Computer Science University of Oxford July 25, 2016 Whiteson & Roijers (UOx) Multi-Objective Decision Making July 25,

More information

Temporal Difference Learning & Policy Iteration

Temporal Difference Learning & Policy Iteration Temporal Difference Learning & Policy Iteration Advanced Topics in Reinforcement Learning Seminar WS 15/16 ±0 ±0 +1 by Tobias Joppen 03.11.2015 Fachbereich Informatik Knowledge Engineering Group Prof.

More information

Online Learning for Markov Decision Processes Applied to Multi-Agent Systems

Online Learning for Markov Decision Processes Applied to Multi-Agent Systems Online Learning for Markov Decision Processes Applied to Multi-Agent Systems Mahmoud El Chamie Behçet Açıkmeşe Mehran Mesbahi Abstract Online learning is the process of providing online control decisions

More information

Markov decision processes (MDP) CS 416 Artificial Intelligence. Iterative solution of Bellman equations. Building an optimal policy.

Markov decision processes (MDP) CS 416 Artificial Intelligence. Iterative solution of Bellman equations. Building an optimal policy. Page 1 Markov decision processes (MDP) CS 416 Artificial Intelligence Lecture 21 Making Complex Decisions Chapter 17 Initial State S 0 Transition Model T (s, a, s ) How does Markov apply here? Uncertainty

More information

Final Exam December 12, 2017

Final Exam December 12, 2017 Introduction to Artificial Intelligence CSE 473, Autumn 2017 Dieter Fox Final Exam December 12, 2017 Directions This exam has 7 problems with 111 points shown in the table below, and you have 110 minutes

More information

Bootstrapping LPs in Value Iteration for Multi-Objective and Partially Observable MDPs

Bootstrapping LPs in Value Iteration for Multi-Objective and Partially Observable MDPs Bootstrapping LPs in Value Iteration for Multi-Objective and Partially Observable MDPs Diederik M. Roijers Vrije Universiteit Brussel & Vrije Universiteit Amsterdam Erwin Walraven Delft University of Technology

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

CS221 Practice Midterm

CS221 Practice Midterm CS221 Practice Midterm Autumn 2012 1 ther Midterms The following pages are excerpts from similar classes midterms. The content is similar to what we ve been covering this quarter, so that it should be

More information

Approximating Reachable Belief Points in POMDPs

Approximating Reachable Belief Points in POMDPs Approximating Reachable Belief Points in POMDPs Kyle Hollins Wray and Shlomo Zilberstein Abstract We propose an algorithm called σ-approximation that compresses the non-zero values of beliefs for partially

More information

Goal Recognition over POMDPs: Inferring the Intention of a POMDP Agent

Goal Recognition over POMDPs: Inferring the Intention of a POMDP Agent Goal Recognition over POMDPs: Inferring the Intention of a POMDP Agent Miquel Ramírez Universitat Pompeu Fabra 08018 Barcelona, SPAIN miquel.ramirez@upf.edu Hector Geffner ICREA & Universitat Pompeu Fabra

More information

Focused Real-Time Dynamic Programming for MDPs: Squeezing More Out of a Heuristic

Focused Real-Time Dynamic Programming for MDPs: Squeezing More Out of a Heuristic Focused Real-Time Dynamic Programming for MDPs: Squeezing More Out of a Heuristic Trey Smith and Reid Simmons Robotics Institute, Carnegie Mellon University {trey,reids}@ri.cmu.edu Abstract Real-time dynamic

More information

Probabilistic inference for computing optimal policies in MDPs

Probabilistic inference for computing optimal policies in MDPs Probabilistic inference for computing optimal policies in MDPs Marc Toussaint Amos Storkey School of Informatics, University of Edinburgh Edinburgh EH1 2QL, Scotland, UK mtoussai@inf.ed.ac.uk, amos@storkey.org

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

Solving Factored MDPs with Continuous and Discrete Variables

Solving Factored MDPs with Continuous and Discrete Variables Appeared in the Twentieth Conference on Uncertainty in Artificial Intelligence, Banff, Canada, July 24. Solving Factored MDPs with Continuous and Discrete Variables Carlos Guestrin Milos Hauskrecht Branislav

More information

The quest for finding Hamiltonian cycles

The quest for finding Hamiltonian cycles The quest for finding Hamiltonian cycles Giang Nguyen School of Mathematical Sciences University of Adelaide Travelling Salesman Problem Given a list of cities and distances between cities, what is the

More information

Constrained Markov Decision Processes

Constrained Markov Decision Processes Constrained Markov Decision Processes Nelson Gonçalves April 16, 2007 Topics Introduction Examples Constrained Markov Decision Process Markov Decision Process Policies Cost functions: The discounted cost

More information

An Analytic Solution to Discrete Bayesian Reinforcement Learning

An Analytic Solution to Discrete Bayesian Reinforcement Learning An Analytic Solution to Discrete Bayesian Reinforcement Learning Pascal Poupart (U of Waterloo) Nikos Vlassis (U of Amsterdam) Jesse Hoey (U of Toronto) Kevin Regan (U of Waterloo) 1 Motivation Automated

More information

CS 188 Introduction to Fall 2007 Artificial Intelligence Midterm

CS 188 Introduction to Fall 2007 Artificial Intelligence Midterm NAME: SID#: Login: Sec: 1 CS 188 Introduction to Fall 2007 Artificial Intelligence Midterm You have 80 minutes. The exam is closed book, closed notes except a one-page crib sheet, basic calculators only.

More information

Final Exam December 12, 2017

Final Exam December 12, 2017 Introduction to Artificial Intelligence CSE 473, Autumn 2017 Dieter Fox Final Exam December 12, 2017 Directions This exam has 7 problems with 111 points shown in the table below, and you have 110 minutes

More information