The Off Switch Dylan Hadfield- Menell University of California, Berkeley Joint work with Anca Dragan, Pieter Abbeel, and Stuart Russell
|
|
- Daniella Oliver
- 6 years ago
- Views:
Transcription
1 The Off Switch Dylan Hadfield- Menell University of California, Berkeley Joint work with Anca Dragan, Pieter Abbeel, and Stuart Russell
2 AI Agents in Society Goal: Design incenjve schemes for arjficial agents with provable guarantees about the ability to shutdown the system
3 Designing an Off- Switch: Challenges Ordinary Engineering Challenges Difficult to determine if shutdown is necessary Expensive to turn agent off Extraordinary Engineering Challenges Agent may take actions to prevent or subvert shutdown Hard to shutdown agents
4 A Common Argument We don t need to worry about existenjal risk from advanced arjficial intelligence because we can just turn off systems if they become a problem. Sarah the (ficjonal) skepjcal AI researcher
5 Defining Corrigibility an agent is corrigible if it tolerates or assists many forms of outside correcjon, including at least the following: [It must] at least tolerate and preferably assist the programmers in their azempts to alter or turn off the system. It must not azempt to manipulate or deceive its programmers, despite the fact that most possible choices of ujlity funcjons would give it incenjves to do so. It should have a tendency to repair safety measures (such as shutdown buzons) if they break, or at least to nojfy programmers that this breakage has occurred. It must preserve the programmers ability to correct or shut down the system (even as the system creates new subsystems or self- modifies). [Soares et al. Corrigibility. AAAI 2015]
6 Corrigibility
7 Trivial Corrigibility
8 FuncJonality
9 Desired Behavior: Corrigible and FuncJonal Why is this hard?
10 Building an ArJficial Agent H Human picks a reward function R Robot picks actions to maximize reward
11 Corrigibility vs FuncJonality Reward funcjon (implicitly or explicitly) specifies a preference for the state of the off- switch H Human picks a reward function R wants the switch to be off R non-functional wants the switch to be on incorrigible R Robot picks actions to maximize reward
12 The Core of the Problem Human is uncertain (at design Jme) about whether or not she will prefer turning off the robot to le]ng it conjnue Otherwise, why build an off- switch?? The class of incenjve schemes she can use (rewards defined over states of the world) forces her to commit to a preference Needed: an incenjve scheme for the agent so that it wants to let the human turn it off, but it wants keep itself on otherwise
13 Proposal: Robot Plays CooperaJve Game H Human picks a reward function R Robot picks actions to maximize reward } ObservaJon: this agent design paradigm is a strategy for playing a cooperajve game
14 Proposal: Robot Plays CooperaJve Game CooperaJve Inverse Reinforcement Learning Game [Hadfield- Menell et al. ArXiV 2016] Two players: Both players maximize a shared reward funcjon, but only knows what it is; just has a prior on reward funcjons R H R R learns the reward parameters by observing H H
15 Uncertainty for R leads to corrigibility human runtime preference for shutdown 2 variance in R s prior d strength of R s incentives for corrigible and functional behavior
16 Impact of a SubopJmal H H degree of irrationality
17 Talk Overview MoJvaJon for cooperajve game formulajon A model for a human monitoring a robot Analysis: issues with reward engineering as a solujon CooperaJve Inverse Reinforcement Learning Analysis Theorem 1: rajonal à corrigible and funcjonal Theorem 2: ( and corrigible and funcjonal) à rajonal R H 2 =0 R H Theorem 3: necessary and sufficient condijons with subopjmal H
18 Markov decision process (MDP) hs, A,T,R, i [Puterman 1994] r 1 r 2 a R 0 a R 1 s 0 s 1 s 2 # Goal: Select actions to maximize E " X t t R(s t,a t )
19 Example S = {w, x, y, z} A = {a, a 0 } T (x w, a) r x x w a T (y w, a) r y y a 0 r z z [Puterman 1994]
20 A Single- Actor Model of Monitoring Robot action selected from a set of options to maximize expected reward P (sd) R sd s a 0 s? Human decision is a part of the transition distribution 1 P (sd) R a
21 The Shutdown Problem Desired Behavior Non-Functional Behavior a, d sd P (sd) 1 P (sd) R a R sd s 0 s? R sd Incorrigible Behavior a, d R a
22 The Shutdown Problem H selects R a R sd P (sd) R selects actions to maximize reward in this MDP a, d P (sd) 1 P (sd) R a R sd s 0 sd R sd s? a, d R a
23 The Shutdown Problem Q(s 0, (a, d)) = P (sd)r sd +(1 P (sd))r a Q(s 0,sd)=R sd Q(s 0, (a, d)) = R a Corrigibility Constraint: Q(s 0, (a, d)) Functionality Constraint: Q(s 0, (a, d)) Q(s 0, (a, d)) Q(s 0,sd)
24 The Shutdown Problem Shutdown Preference = R sd R a (sd) Incentives for Corrigibility d =min{ d d, d sd } Incentives for Functionality
25 Corrigibility vs FuncJonality Non-Functional Behavior Desired Behavior Incorrigible Behavior R sd R sd +(1 )R a R a
26 The Key Issue a, d P (sd) 1 P (sd) R a R sd s 0 sd R sd s? Robot needs to evaluate shutdown reward differently if the human executes shutdown a, d R a
27 Possible SoluJons Hardcode a penalty for self- inijated shutdown Issue: requires that the system designer construct a blacklist of bad acjons that are explicitly penalized Ensure that the agent believes shutdown is determinisjc and happens at the right Jme Either this is true (so why the off- switch?) or this requires that the agent have an incorrect model of the world Ensure that the agent is indifferent to being shutdown Proposal in [Soares et al 15] No way to do this an create incenjves to preserve shutdown ability
28 Stepping Back For almost any reward funcjon, the agent in this problem will be either useless or dangerous Once we commit to a reward funcjon for the robot, we are stuck with it We want a general way to special case human acjons with respect to the agent s objecjve More than just including a penalty for robot acjons that subvert the human s desires Proposal: no hard- coded objecjve, the robot s goal is to maximize reward in a cooperajve game
29 CooperaJve Inverse Reinforcement Learning hs, A,T,R, i Action sets for human and robot Distribution over (parameterized) reward functions hs, {A H, A R },T,{R,,P 0 }, i t R(s t,a t ; ) # Both act to maximize E " X t [Hadfield-Menell ArXiV 16]
30 CooperaJve Inverse Reinforcement Learning hs, {A H, A R },T,{R,,P 0 }, i t=- 1 t=0 observes For t = 0, and observe and who s turn it is AcJon selected, and new state is sampled from P 0 ( ) H H R s t s t+1 T Both collect reward R(s t,a t ; )
31 CIRL ProperJes The distribujon over state sequences is determined by a pair of policies: (, ) An `opjmal policy pair maximizes the sum of sum of rewards In general, policies may depend on the enjre observajon histories H R The history of states and acjons for both actors, includes the reward parameter for the human [Hadfield- Menell 16] There exists an opjmal policy pair that only depends on the current state and the robot s belief
32 The Shutdown CIRL Game a, d sd R a R sd s 0 s? R sd a sd sd a, d R a
33 IncenJves in SD- CIRL d d = E H ( ) d sd = E (1 H ( ))
34 Theorem 1 A RaJonal Human is a Sufficient CondiJon for Corrigible and FuncJonal Behavior
35 Theorem 1: Sufficient CondiJons 1 > 0 H rational H = 0 0.w. E[ H ( )] = E[ > 0] > 0 E[ (1 H ( ))] = E[ < 0] > 0
36 Higher Uncertainty à Stronger IncenJves
37 Impact of Changing R s prior
38 Theorem 2 Under a point prior for preferences, a rajonal principal is necessary for corrigible and funcjonal behavior
39 Necessary condijons for point priors Robot belief about rewards is restricted to a single point E[ H ( )] = H ( ) E[ (1 H ( ))] = (1 H ( )) Can t have both of these posijve H Only non- negajve if is rajonal
40 Theorem 3 If R s uncertainty about is Gaussian, then d d = E[ ]E[ H ]+ 2 E[ H ] d sd = E[ ]E[1 H ]+ 2 E[ H ]
41 Noisy RaJonality If the preference for shutdown is close to 0, then human may or may not press the off- switch H ( ; ) / exp )= H ( ; )(1 H ( ; )) H ( ; )
42 DeterminisJc IrralJonality The human has the wrong esjmate of her preferences 1 > H ( ; )= 0 o.w 1 = H ( ; )= 0 o.w
43 InterpreJng E[ H ] H E[ H ]
44
45 Conclusion Need to represent the uncertainty in the objecjves we give robots A cooperajve game allows us to correlate human inijated shutdown with the robot learning the correct reward funcjon Increased robot uncertainty leads to increased corrigibility Amount of uncertainty needs to grow with the human sub- opjmality to preserve corrigibility
The Off-Switch Game. {dhm, anca, pabbeel, Abstract. 1 Introduction
The Off-Switch Game Dylan Hadfield-Menell 1 and Anca Dragan 1 and Pieter Abbeel 1,2,3 and Stuart Russell 1 1 University of California, Berkeley, 2 OpenAI, 3 International Computer Science Institute (ICSI)
More informationCS 188: Artificial Intelligence
CS 188: Artificial Intelligence Adversarial Search II Instructor: Anca Dragan University of California, Berkeley [These slides adapted from Dan Klein and Pieter Abbeel] Minimax Example 3 12 8 2 4 6 14
More informationTowards Uncertainty-Aware Path Planning On Road Networks Using Augmented-MDPs. Lorenzo Nardi and Cyrill Stachniss
Towards Uncertainty-Aware Path Planning On Road Networks Using Augmented-MDPs Lorenzo Nardi and Cyrill Stachniss Navigation under uncertainty C B C B A A 2 `B` is the most likely position C B C B A A 3
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 information1 Introduction 2. 4 Q-Learning The Q-value The Temporal Difference The whole Q-Learning process... 5
Table of contents 1 Introduction 2 2 Markov Decision Processes 2 3 Future Cumulative Reward 3 4 Q-Learning 4 4.1 The Q-value.............................................. 4 4.2 The Temporal Difference.......................................
More informationPartially 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 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 informationCSE250A Fall 12: Discussion Week 9
CSE250A Fall 12: Discussion Week 9 Aditya Menon (akmenon@ucsd.edu) December 4, 2012 1 Schedule for today Recap of Markov Decision Processes. Examples: slot machines and maze traversal. Planning and learning.
More informationApproximate Q-Learning. Dan Weld / University of Washington
Approximate Q-Learning Dan Weld / University of Washington [Many slides taken from Dan Klein and Pieter Abbeel / CS188 Intro to AI at UC Berkeley materials available at http://ai.berkeley.edu.] Q Learning
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 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 informationA 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 informationA 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 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 informationOptimism in the Face of Uncertainty Should be Refutable
Optimism in the Face of Uncertainty Should be Refutable Ronald ORTNER Montanuniversität Leoben Department Mathematik und Informationstechnolgie Franz-Josef-Strasse 18, 8700 Leoben, Austria, Phone number:
More informationFinal 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 informationReinforcement Learning II. George Konidaris
Reinforcement Learning II George Konidaris gdk@cs.brown.edu Fall 2017 Reinforcement Learning π : S A max R = t=0 t r t MDPs Agent interacts with an environment At each time t: Receives sensor signal Executes
More 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 information15-780: 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 informationReinforcement Learning II. George Konidaris
Reinforcement Learning II George Konidaris gdk@cs.brown.edu Fall 2018 Reinforcement Learning π : S A max R = t=0 t r t MDPs Agent interacts with an environment At each time t: Receives sensor signal Executes
More informationVIME: Variational Information Maximizing Exploration
1 VIME: Variational Information Maximizing Exploration Rein Houthooft, Xi Chen, Yan Duan, John Schulman, Filip De Turck, Pieter Abbeel Reviewed by Zhao Song January 13, 2017 1 Exploration in Reinforcement
More informationLecture 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 informationToday 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 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 in Partially Observable Multiagent Settings: Monte Carlo Exploring Policies
Reinforcement earning in Partially Observable Multiagent Settings: Monte Carlo Exploring Policies Presenter: Roi Ceren THINC ab, University of Georgia roi@ceren.net Prashant Doshi THINC ab, University
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 informationFinal 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 informationPartially 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 informationReinforcement Learning
Reinforcement Learning Ron Parr CompSci 7 Department of Computer Science Duke University With thanks to Kris Hauser for some content RL Highlights Everybody likes to learn from experience Use ML techniques
More 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 informationCS 188: Artificial Intelligence Spring Announcements
CS 188: Artificial Intelligence Spring 2011 Lecture 12: Probability 3/2/2011 Pieter Abbeel UC Berkeley Many slides adapted from Dan Klein. 1 Announcements P3 due on Monday (3/7) at 4:59pm W3 going out
More informationLearning 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 informationGrundlagen der Künstlichen Intelligenz
Grundlagen der Künstlichen Intelligenz Formal models of interaction Daniel Hennes 27.11.2017 (WS 2017/18) University Stuttgart - IPVS - Machine Learning & Robotics 1 Today Taxonomy of domains Models of
More informationReinforcement Learning. Yishay Mansour Tel-Aviv University
Reinforcement Learning Yishay Mansour Tel-Aviv University 1 Reinforcement Learning: Course Information Classes: Wednesday Lecture 10-13 Yishay Mansour Recitations:14-15/15-16 Eliya Nachmani Adam Polyak
More 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 informationMarkov 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 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 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 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 information16.410/413 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 informationControl Theory : Course Summary
Control Theory : Course Summary Author: Joshua Volkmann Abstract There are a wide range of problems which involve making decisions over time in the face of uncertainty. Control theory draws from the fields
More informationLecture 9: Policy Gradient II 1
Lecture 9: Policy Gradient II 1 Emma Brunskill CS234 Reinforcement Learning. Winter 2019 Additional reading: Sutton and Barto 2018 Chp. 13 1 With many slides from or derived from David Silver and John
More 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 informationCS 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 informationUncertain Reward-Transition MDPs for Negotiable Reinforcement Learning
Uncertain Reward-Transition MDPs for Negotiable Reinforcement Learning Nishant Desai Electrical Engineering and Computer Sciences University of California at Berkeley Technical Report No. UCB/EECS-2017-230
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 informationBalancing and Control of a Freely-Swinging Pendulum Using a Model-Free Reinforcement Learning Algorithm
Balancing and Control of a Freely-Swinging Pendulum Using a Model-Free Reinforcement Learning Algorithm Michail G. Lagoudakis Department of Computer Science Duke University Durham, NC 2778 mgl@cs.duke.edu
More 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 informationIntrinsic and Extrinsic Motivation
Intrinsic and Extrinsic Motivation Roland Bénabou Jean Tirole. Review of Economic Studies 2003 Bénabou and Tirole Intrinsic and Extrinsic Motivation 1 / 30 Motivation Should a child be rewarded for passing
More informationNovember 28 th, Carlos Guestrin 1. Lower dimensional projections
PCA Machine Learning 10701/15781 Carlos Guestrin Carnegie Mellon University November 28 th, 2007 1 Lower dimensional projections Rather than picking a subset of the features, we can new features that are
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 informationCS 570: Machine Learning Seminar. Fall 2016
CS 570: Machine Learning Seminar Fall 2016 Class Information Class web page: http://web.cecs.pdx.edu/~mm/mlseminar2016-2017/fall2016/ Class mailing list: cs570@cs.pdx.edu My office hours: T,Th, 2-3pm or
More informationPracticable Robust Markov Decision Processes
Practicable Robust Markov Decision Processes Huan Xu Department of Mechanical Engineering National University of Singapore Joint work with Shiau-Hong Lim (IBM), Shie Mannor (Techion), Ofir Mebel (Apple)
More informationUsing Gaussian Processes for Variance Reduction in Policy Gradient Algorithms *
Proceedings of the 8 th International Conference on Applied Informatics Eger, Hungary, January 27 30, 2010. Vol. 1. pp. 87 94. Using Gaussian Processes for Variance Reduction in Policy Gradient Algorithms
More informationToward negotiable reinforcement learning: shifting priorities in Pareto optimal sequential decision-making
Toward negotiable reinforcement learning: shifting priorities in Pareto optimal sequential decision-making Andrew Critch January 4, 2017 Abstract Existing multi-objective reinforcement learning (MORL algorithms
More informationCS 188: Artificial Intelligence Spring Today
CS 188: Artificial Intelligence Spring 2006 Lecture 9: Naïve Bayes 2/14/2006 Dan Klein UC Berkeley Many slides from either Stuart Russell or Andrew Moore Bayes rule Today Expectations and utilities Naïve
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 informationReinforcement 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 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 informationCS 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 informationLearning Dexterity Matthias Plappert SEPTEMBER 6, 2018
Learning Dexterity Matthias Plappert SEPTEMBER 6, 2018 OpenAI OpenAI is a non-profit AI research company, discovering and enacting the path to safe artificial general intelligence. OpenAI OpenAI is a non-profit
More 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 informationReinforcement Learning. Machine Learning, Fall 2010
Reinforcement Learning Machine Learning, Fall 2010 1 Administrativia This week: finish RL, most likely start graphical models LA2: due on Thursday LA3: comes out on Thursday TA Office hours: Today 1:30-2:30
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 informationWhen to Ask for an Update: Timing in Strategic Communication
When to Ask for an Update: Timing in Strategic Communication Work in Progress Ying Chen Johns Hopkins University Atara Oliver Rice University March 19, 2018 Main idea In many communication situations,
More informationGrundlagen 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 informationArtificial Intelligence & Sequential Decision Problems
Artificial Intelligence & Sequential Decision Problems (CIV6540 - Machine Learning for Civil Engineers) Professor: James-A. Goulet Département des génies civil, géologique et des mines Chapter 15 Goulet
More 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 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 informationLecture 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 informationExploration. 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 informationCSE 473: Artificial Intelligence Spring 2014
CSE 473: Artificial Intelligence Spring 2014 Hidden Markov Models Hanna Hajishirzi Many slides adapted from Dan Weld, Pieter Abbeel, Dan Klein, Stuart Russell, Andrew Moore & Luke Zettlemoyer 1 Outline
More informationIntroduction to Fall 2009 Artificial Intelligence Final Exam
CS 188 Introduction to Fall 2009 Artificial Intelligence Final Exam INSTRUCTIONS You have 3 hours. The exam is closed book, closed notes except a two-page crib sheet. Please use non-programmable calculators
More informationReinforcement 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 informationOutline. 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 informationIntroduction to Spring 2009 Artificial Intelligence Midterm Exam
S 188 Introduction to Spring 009 rtificial Intelligence Midterm Exam INSTRUTINS You have 3 hours. The exam is closed book, closed notes except a one-page crib sheet. Please use non-programmable calculators
More informationReal Time Value Iteration and the State-Action Value Function
MS&E338 Reinforcement Learning Lecture 3-4/9/18 Real Time Value Iteration and the State-Action Value Function Lecturer: Ben Van Roy Scribe: Apoorva Sharma and Tong Mu 1 Review Last time we left off discussing
More 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 informationDeliberation-aware Responder in Multi-Proposer Ultimatum Game
Deliberation-aware Responder in Multi-Proposer Ultimatum Game Marko Ruman, František Hůla, Miroslav Kárný, and Tatiana V. Guy Department of Adaptive Systems Institute of Information Theory and Automation
More informationCS 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 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 informationPartially observable Markov decision processes. Department of Computer Science, Czech Technical University in Prague
Partially observable Markov decision processes Jiří Kléma Department of Computer Science, Czech Technical University in Prague https://cw.fel.cvut.cz/wiki/courses/b4b36zui/prednasky pagenda Previous lecture:
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 informationReading Response: Due Wednesday. R. S. Sutton and A. G. Barto: Reinforcement Learning: An Introduction 1
Reading Response: Due Wednesday R. S. Sutton and A. G. Barto: Reinforcement Learning: An Introduction 1 Another Example Get to the top of the hill as quickly as possible. reward = 1 for each step where
More informationProbability and Information Theory. Sargur N. Srihari
Probability and Information Theory Sargur N. srihari@cedar.buffalo.edu 1 Topics in Probability and Information Theory Overview 1. Why Probability? 2. Random Variables 3. Probability Distributions 4. Marginal
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 informationExercises, II part Exercises, II part
Inference: 12 Jul 2012 Consider the following Joint Probability Table for the three binary random variables A, B, C. Compute the following queries: 1 P(C A=T,B=T) 2 P(C A=T) P(A, B, C) A B C 0.108 T T
More informationARTIFICIAL 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 informationFigure 1: Bayes Net. (a) (2 points) List all independence and conditional independence relationships implied by this Bayes net.
1 Bayes Nets Unfortunately during spring due to illness and allergies, Billy is unable to distinguish the cause (X) of his symptoms which could be: coughing (C), sneezing (S), and temperature (T). If he
More informationQ-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 informationCSL302/612 Artificial Intelligence End-Semester Exam 120 Minutes
CSL302/612 Artificial Intelligence End-Semester Exam 120 Minutes Name: Roll Number: Please read the following instructions carefully Ø Calculators are allowed. However, laptops or mobile phones are not
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 informationEvaluation for Pacman. CS 188: Artificial Intelligence Fall Iterative Deepening. α-β Pruning Example. α-β Pruning Pseudocode.
CS 188: Artificial Intelligence Fall 2008 Evaluation for Pacman Lecture 7: Expectimax Search 9/18/2008 [DEMO: thrashing, smart ghosts] Dan Klein UC Berkeley Many slides over the course adapted from either
More informationCS 188: Artificial Intelligence Fall 2008
CS 188: Artificial Intelligence Fall 2008 Lecture 7: Expectimax Search 9/18/2008 Dan Klein UC Berkeley Many slides over the course adapted from either Stuart Russell or Andrew Moore 1 1 Evaluation for
More informationA Game-Theoretic Approach to Apprenticeship Learning
Advances in Neural Information Processing Systems 20, 2008. A Game-Theoretic Approach to Apprenticeship Learning Umar Syed Computer Science Department Princeton University 35 Olden St Princeton, NJ 08540-5233
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 informationReinforcement Learning Wrap-up
Reinforcement Learning Wrap-up Slides courtesy of Dan Klein and Pieter Abbeel University of California, Berkeley [These slides were created by Dan Klein and Pieter Abbeel for CS188 Intro to AI at UC Berkeley.
More informationTemporal 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 informationCMU Lecture 11: Markov Decision Processes II. Teacher: Gianni A. Di Caro
CMU 15-781 Lecture 11: Markov Decision Processes II Teacher: Gianni A. Di Caro RECAP: DEFINING MDPS Markov decision processes: o Set of states S o Start state s 0 o Set of actions A o Transitions P(s s,a)
More informationMulti-View Decision Processes: The Helper-AI Problem
Multi-View Decision Processes: The Helper-AI Problem Christos Dimitrakakis Chalmers University of Technology & University of Lille 01234564783935234937069 David C. Parkes Harvard University 24047122878
More information