Reinforcement Learning
|
|
- Shawn Fowler
- 6 years ago
- Views:
Transcription
1 Reinforcement Learning Hierarchical Reinforcement Learning Action hierarchy, hierarchical RL, semi-mdp Vien Ngo Marc Toussaint University of Stuttgart
2 Outline Hierarchical reinforcement learning Learning subgoals/hierarchy 2/??
3 Accelerating Reinforcement learning Temporal abstraction Goal/State Abstraction 3/??
4 Accelerating Reinforcement learning: Abstraction Temporal abstraction Goal/State Abstraction 4/??
5 Temporal Abstraction Dealing with multiple-time step macro actions. Advantages: Only exploring/computing values for interesting states (e.i. subgoals,... ) Transfer learning across problems/regions. 5/??
6 Hierarchical reinforcement learning Three approaches to HRL Options: Sutton (temporal + state abstraction) Finite state controller: Parr & Russel (temporal abstraction) Given an action hierarchy: MAXQ (temporal + state abstraction) 6/??
7 Semi-Markov decision process 7/??
8 Semi-Markov decision process SMDP = {S, A, T, R}, State space S Action space A Transition function T(s, a, s, t) = p(s, t s, a) State space R(s, a) 8/??
9 SMDP Semi-Markov decision processes (SMDPs) generalize MDPs by allowing the decision maker to choose actions whenever the system state changes modeling the system evolution in continuous time allowing the time spent in a particular state to follow an arbitrary probability distribution The system state may change several times between decision epochs; only the state at a decision epoch is relevant to the decision maker. 9/??
10 Semi-Markov Decision Process (SMDP) T(s, a, s, t) = P (s, t s, a) defines the joint probability of a next state, and terminal time. 10/??
11 Bellman equations for SMDP Consider discrete-time SMDP: [ V (s) = max R(s, a) + γ ] τ p(s, τ s, a)v (s ) a s,τ Q (s, a) = R(s, a) + γ τ s,τ p(s, τ s, a) max Q (s, b) b 11/??
12 Bellman equations for SMDP Consider discrete-time SMDP: [ V (s) = max R(s, a) + γ ] τ p(s, τ s, a)v (s ) a s,τ Q (s, a) = R(s, a) + γ τ s,τ p(s, τ s, a) max Q (s, b) b Dynamic Programming algorithms are correspondingly extended to SMDPs (Howard, 1971; Puterman, 1994) 11/??
13 Example: Taxi Problem R G ROOT GET PUT pickup putdown NAVIGATE to Red Y B north south east west 12/??
14 Example 2: SMDP Sutton, Precup, Singh, /??
15 Example 2: SMDP Sutton, Precup, Singh, /??
16 Example 2: SMDP Sutton, Precup, Singh, /??
17 Options Sutton, Precup, Singh, /??
18 Options An option is a triple o =< I, π, β > I: initiation set. π : S A [0, 1]: option s policy [ ] β : S 0, 1 : termination condition 17/??
19 Options 18/??
20 Value Functions for Options option s policy: π i ; global policy: µ Denote reward part of option: { } r(s, o) = E r t+1 + γr t+2 + γ 2 r t γ k r t+k o, s t = s prediction-state part: p(s s, o) = p(s, k s, o)γ k k=1 Global policy s value function { } V µ (s) = E r t + γr t+1 + γ 2 r t+2... µ, s t = s { } = E r t+1 + γr t+2 + γ 2 r t γ k 1 r t+k + γ k V µ (s t+k ) µ, s t = s [ = E r(s, o) + ] p(s t+k s, o)v µ (s ) µ, s t = s s t+k 19/??
21 { } Q µ (s, o) = E r t + γr t+1 + γ 2 r t+2... oµ, s t = s { } = E r t+1 + γr t+2 + γ 2 r t γ k 1 r t+k + γ k V µ (s t+k ) µ, s t = s { = E r t+1 + γr t+2 + γ 2 r t γ k 1 r t+k } + max µ(s t+k, o )Q µ (s t+k, o ) oµ, s t = s o = r(s, o) + p(s t+k s, o) max µ(s t+k, o )Q µ (s t+k, o ) o 20/??
22 Options: Learning SMDP Q-learning: given the set of defined options. execute the current selected option (e.g use epsilon greedy Q(s, o)) to termination. compute r(s t, o), then update Q(s t, o) as Q-learning/SARSA. 21/??
23 Options: Learning SMDP Q-learning: given the set of defined options. execute the current selected option (e.g use epsilon greedy Q(s, o)) to termination. compute r(s t, o), then update Q(s t, o) as Q-learning/SARSA. Intra-option Q-learning: partially defined options after each primitive action, update all the options (off-policy learning). converge to correct values, under same assumptions as 1-step Q-learning (Sutton) 21/??
24 Hierarchies of Abstract Machines (HAM) Parr (1998) and Parr and Russell (1988) 22/??
25 HAM A HAM is a program which constrains the actions that the agent can take in each state. Each machine is defined by: a set of states, a transition function, and a start function. Machine states m: Action, Call, Choice, Stop. The transition function: a stochastic function of the current machine state and some features of the resulting environment state to determine the next machine state. Start function that determines the initial state of the machine. 23/??
26 HAM: Learning 24/??
27 RL with HAM H MDP = SMDP. Given defined HAMs, finding policy a t = π(s t, m t ) (actions are choices made by machines). Given HAM means: similar to given well defined options o, then finding π(s, o). 25/??
28 MAXQ T. G. Dietterich (2000) Hierarchical Reinforcement Learning with the MAXQ Value Function Decomposition, JAIR. 26/??
29 MAXQ The underlying MDP M is decomposed into a set of substask M 0, M 1,..., M n. M 0 is the root subtask. (solving M 0 solves M). Each substask might consist of either primitive actions or other substasks. example: TAXI problem. 27/??
30 MAXQ: Value Decomposition Consider all descendents a of a subtask M i (or option M i ) { } V µ (i, s) = E r t + γr t+1 + γ 2 r t+2... µ, s t = s (until M i terminates) { } = E r t+1 + γr t γ k 1 r t+k + γ k V µ (s t+k ) µ, s t = s [ ] = E r(s, π i (s)) + +γ k 1 r t+k + γ k V µ (i, s t+k ) µ, s t = s = V µ (π i (s), s) + p(s, N s, π i (s))γ N V µ (i, s ) }{{} s reward term,n }{{} C µ (i,s,π i(s))(completion term) Q µ (i, s, a) = V µ (a, s) + C µ (i, s, a) The reward term: V µ Q µ (i, s, π i (s)) (i, s) = s P (s s, a)r(s s, a) If i is a macro action If i is an primitive action 28/??
31 The completion term C µ (i, s, a) is the expected discounted cummulative reward of completing subtask M i after taking subroutine M a in state s. 29/??
32 The completion term C µ (i, s, a) is the expected discounted cummulative reward of completing subtask M i after taking subroutine M a in state s. It recursively decompose V µ (0, s) into value functions for M 1, M 2,..., M n. 29/??
33 The completion term C µ (i, s, a) is the expected discounted cummulative reward of completing subtask M i after taking subroutine M a in state s. It recursively decompose V µ (0, s) into value functions for M 1, M 2,..., M n. In general: V µ (0, s) = V µ (a m, s)+c µ (a m 1, s, a m )+...+C µ (a 1, s, a 2 )+C µ (0, s, a 1 ) where a 0, a 1,..., a m is a sequence of taken substasks by a hierarchical policy going from Root M 0. For learning: only need to store C functions for non-primitive actions, and V for primitive actions. 29/??
34 Example of MAXQ value decomposition r 1, r 2,..., r 14 is a sequence of rewards w.r.t primitve actions at times 1, 2,..., /??
35 MAXQ: Learning Algorithm MAXQ-0 learning algorithm Given action hierarchy. Each subtask has zero pseudo terminal reward. 31/??
36 MAXQ-0 Learning Algorithm Initialize V (i, s) (for all primitive i) and C(i, s, j) (for all non-primitive i, and descendents j of i) arbitrarily. MAXQ-0(Node i, State s) 1: if i is primitve then 2: execute i, receive r, s 3: V t+1 (i, s) = (1 α)v t (i, s) + αr t 4: else 5: steps = 0 6: while i not terminates do 7: Choose a π i (s) (e.g. arg max b Q(i, s, b))) 8: call N = MAXQ-0(a, s) (recursive call) 9: observe s 10: C t+1 (i, s, a) = (1 α)c t (i, s, a) + α.γ N.V t (i, s ) 11: steps = steps + N 12: s = s 13: end while 14: end if 32/??
37 MAXQ-0 Learning Algorithm Compute V t (i, s ) if i is non-primitive? 33/??
38 MAXQ-0 Learning Algorithm Compute V t (i, s ) if i is non-primitive? max a Q t (i, s, a) V t (i, s) = V t (i, s) If i is a macro action If i is an primitive action Q t (i, s, a) = V t (a, s) + C t (i, s, a) 33/??
39 MAXQ: Learning Algorithm Given action hierarchy. MAXQ-Q learning algorithm When Each subtask has arbitrary non-zero pseudo reward R i. MAXQ-Q introduces one more completion function for each subtask to use inside itself. 34/??
40 MAXQ-Q Learning Algorithm Initialize V (i, s) (for all primitive i) and C(i, s, j) and C(i, s, j) (for all non-primitive i, and descendents j of i) arbitrarily. MAXQ-Q(Node i, State s) 1: if i is primitve then 2: execute i, receive r, s 3: V t+1 (i, s) = (1 α)v t(i, s) + αr t 4: else 5: steps = 0 6: while i not terminates do 7: Choose a π i (s) (arg max a [ C(i, s, a ) + V (i, s )]) 8: call N = MAXQ-Q(a, s) (recursive call) 9: observe s 10: a = arg max a [ C(i, s, a ) + V (i, s )] 11: Ct+1 (i, s, a) = (1 α) C t(i, s, a) + α.γ.( N Ri (s ) + C ) t(i, s, a ) + V t(a, s ) ( ) 12: C t+1 (i, s, a) = (1 α)c t(i, s, a) + α.γ N. C t(i, s, a ) + V t(a, s ) 13: steps = steps + N 14: s = s 15: end while 16: end if 35/??
41 Optimality in HRL? 36/??
42 Optimality in HRL? hierarchically optimal vs. recursively optimal Hierarchical optimality: The learnt policy is the best policy consistent with the given hierarchy. Task s policy depends not only on its children s policies, but also on its context. Recursive optimality: The policy for a parent task is optimal given the learnt policies of its children. (Context-free task s policy). 37/??
43 Optimality in HRL? hierarchically optimal vs. recursively optimal Hierarchical optimality: The learnt policy is the best policy consistent with the given hierarchy. Task s policy depends not only on its children s policies, but also on its context. Recursive optimality: The policy for a parent task is optimal given the learnt policies of its children. (Context-free task s policy). The context-free policies offer state abstraction/transfer learning better, which provides common macro actions to many other tasks. 37/??
44 Optimality in HRL (an example from a tutorial of Dietterich). 38/??
45 Optimality: in Options If action space consists of both primitive actions and options, the it converges to an optimal policy. Otherwise, options with SMDP learning was proved to converge to a hierarchically optimal policy. (an example from a tutorial of Dietterich). 39/??
46 Opimality: in HAM π(s 1 ) = South, π(s 2 ) = {North, South} Proved to be hierarchically optimal. (an example from a tutorial of Dietterich). 40/??
47 Optimality: in MAXQ Root Exit ToGoal South North East (an example from a tutorial of Dietterich). 41/??
48 Optimality: in MAXQ Root Exit ToGoal South North East MAXQ is recursively optimal. (an example from a tutorial of Dietterich). 41/??
49 Optimality in HRL? Options/HAM learns a hierarchically optimal policy. MAXQ learns a recursively optimal policy. MAXQ can obtain a policy which has hierarchical optimality with good design of subtask or pseudo-rewards. 42/??
50 Hierarchy/subgoal learning 43/??
51 Subgoal learning Creating usefull options randomly/heuristically, then adding gradually. 44/??
52 Subgoal learning Creating usefull options randomly/heuristically, then adding gradually. Creating an option/subgoal w.r.t a bottltneck (commonalities across multiple paths to a solution). 44/??
53 Hierarchy/subgoal learning Amy McGovern, Andrew G. Barto, Barto et. al. (2004, intrinsically motivated learning) Hengst, (also use bottleneck) Neville Mehta et. al (using DBN) etc. 45/??
54 Human hierarchical decision making JJF Ribas-Fernandes, A Solway, C Diuk, JT McGuire, AG Barto, Y Niv & MM Botvinick (2011) - A neural signature of hierarchical reinforcement learning - Neuron 71: /??
Temporal Abstraction in RL
Temporal Abstraction in RL How can an agent represent stochastic, closed-loop, temporally-extended courses of action? How can it act, learn, and plan using such representations? HAMs (Parr & Russell 1998;
More informationTemporal Abstraction in RL. Outline. Example. Markov Decision Processes (MDPs) ! Options
Temporal Abstraction in RL Outline How can an agent represent stochastic, closed-loop, temporally-extended courses of action? How can it act, learn, and plan using such representations?! HAMs (Parr & Russell
More informationThe Problem of Temporal Abstraction
The Problem of Temporal Abstraction How do we connect the high level to the low-level? " the human level to the physical level? " the decide level to the action level? MDPs are great, search is great,
More informationCausal Graph Based Decomposition of Factored MDPs
Journal of Machine Learning Research 7 (2006) 2259-2301 Submitted 10/05; Revised 7/06; Published 11/06 Causal Graph Based Decomposition of Factored MDPs Anders Jonsson Departament de Tecnologia Universitat
More informationCompositional Planning Using Optimal Option Models
David Silver d.silver@cs.ucl.ac.uk Kamil Ciosek k.ciosek@cs.ucl.ac.uk Department of Computer Science, CSML, University College London, Gower Street, London WC1E 6BT. Abstract In this paper we introduce
More informationReinforcement Learning
Reinforcement Learning MDP March May, 2013 MDP MDP: S, A, P, R, γ, µ State can be partially observable: Partially Observable MDPs () Actions can be temporally extended: Semi MDPs (SMDPs) and Hierarchical
More informationSequential Decision Making
Sequential Decision Making Dynamic programming Christos Dimitrakakis Intelligent Autonomous Systems, IvI, University of Amsterdam, The Netherlands March 18, 2008 Introduction Some examples Dynamic programming
More informationReinforcement Learning Lectures 4 and 5
Reinforcement Learning Lectures 4 and 5 Gillian Hayes 18th January 2007 Reinforcement Learning 1 Framework Rewards, Returns Environment Dynamics Components of a Problem Values and Action Values, V and
More informationIntra-Option Learning about Temporally Abstract Actions
Intra-Option Learning about Temporally Abstract Actions Richard S. Sutton Department of Computer Science University of Massachusetts Amherst, MA 01003-4610 rich@cs.umass.edu Doina Precup Department of
More informationComplex Decisions. Sequential Decision Making
Sequential Decision Making Outline Sequential decision problems Value iteration Policy iteration POMDPs (basic concepts) Slides partially based on the Book "Reinforcement Learning: an introduction" by
More informationBetween MDPs and semi-mdps: A framework for temporal abstraction in reinforcement learning
Artificial Intelligence 112 (1999) 181 211 Between MDPs and semi-mdps: A framework for temporal abstraction in reinforcement learning Richard S. Sutton a,, Doina Precup b, Satinder Singh a a AT&T Labs.-Research,
More informationThe Agent-Environment Interface Goals, Rewards, Returns The Markov Property The Markov Decision Process Value Functions Optimal Value Functions
The Agent-Environment Interface Goals, Rewards, Returns The Markov Property The Markov Decision Process Value Functions Optimal Value Functions Optimality and Approximation Finite MDP: {S, A, R, p, γ}
More informationReinforcement Learning (1): Discrete MDP, Value Iteration, Policy Iteration
Reinforcement Learning (1): Discrete MDP, Value Iteration, Policy Iteration Piyush Rai CS5350/6350: Machine Learning November 29, 2011 Reinforcement Learning Supervised Learning: Uses explicit supervision
More informationReinforcement Learning (1): Discrete MDP, Value Iteration, Policy Iteration
Reinforcement Learning (1): Discrete MDP, Value Iteration, Policy Iteration Piyush Rai CS5350/6350: Machine Learning November 29, 2011 Reinforcement Learning Supervised Learning: Uses explicit supervision
More informationDecision Theory: Value Iteration
Decision Theory: Value Iteration CPSC 322 Decision Theory 4 Textbook 9.5 Decision Theory: Value Iteration CPSC 322 Decision Theory 4, Slide 1 Lecture Overview 1 Recap 2 Policies 3 Value Iteration Decision
More informationMarkov Decision Processes: Making Decision in the Presence of Uncertainty. (some of) R&N R&N
Markov Decision Processes: Making Decision in the Presence of Uncertainty (some of) R&N 16.1-16.6 R&N 17.1-17.4 Different Aspects of Machine Learning Supervised learning Classification - concept learning
More informationCS 188: Artificial Intelligence Spring Announcements
CS 188: Artificial Intelligence Spring 2011 Lecture 9: MDPs 2/16/2011 Pieter Abbeel UC Berkeley Many slides over the course adapted from either Dan Klein, Stuart Russell or Andrew Moore 1 Announcements
More informationIntroduction to Reinforcement Learning. MAL Seminar
Introduction to Reinforcement Learning MAL Seminar 2014-2015 RL Background Learning by interacting with the environment Reward good behavior, punish bad behavior Trial & Error Combines ideas from psychology
More informationIntro to Reinforcement Learning. Part 3: Core Theory
Intro to Reinforcement Learning Part 3: Core Theory Interactive Example: You are the algorithm! Finite Markov decision processes (finite MDPs) dynamics p p p Experience: S 0 A 0 R 1 S 1 A 1 R 2 S 2 A 2
More information4 Reinforcement Learning Basic Algorithms
Learning in Complex Systems Spring 2011 Lecture Notes Nahum Shimkin 4 Reinforcement Learning Basic Algorithms 4.1 Introduction RL methods essentially deal with the solution of (optimal) control problems
More informationNon-Deterministic Search
Non-Deterministic Search MDP s 1 Non-Deterministic Search How do you plan (search) when your actions might fail? In general case, how do you plan, when the actions have multiple possible outcomes? 2 Example:
More informationLecture 17: More on Markov Decision Processes. Reinforcement learning
Lecture 17: More on Markov Decision Processes. Reinforcement learning Learning a model: maximum likelihood Learning a value function directly Monte Carlo Temporal-difference (TD) learning COMP-424, Lecture
More informationReinforcement Learning and Simulation-Based Search
Reinforcement Learning and Simulation-Based Search David Silver Outline 1 Reinforcement Learning 2 3 Planning Under Uncertainty Reinforcement Learning Markov Decision Process Definition A Markov Decision
More informationMDPs: Bellman Equations, Value Iteration
MDPs: Bellman Equations, Value Iteration Sutton & Barto Ch 4 (Cf. AIMA Ch 17, Section 2-3) Adapted from slides kindly shared by Stuart Russell Sutton & Barto Ch 4 (Cf. AIMA Ch 17, Section 2-3) 1 Appreciations
More informationBetween MDPs and Semi-MDPs: Learning, Planning, and Representing Knowledge at Multiple Temporal Scales
Journal of Artificial Intelligence Research 1 (1998) 1-39 Submitted 3/98; published NOT Between MDPs and Semi-MDPs: Learning, Planning, and Representing Knowledge at Multiple Temporal Scales Richard S.
More informationLearning in a Small World
Learning in a Small World Arun Tejasvi Chaganty Deptt. of Computer Science and Engineering, IIT Madras Chennai, India - 600036 arunc@cse.iitm.ac.in Prateek Gaur Deptt. of Computer Science and Engineering,
More informationCSE 473: Artificial Intelligence
CSE 473: Artificial Intelligence Markov Decision Processes (MDPs) Luke Zettlemoyer Many slides over the course adapted from Dan Klein, Stuart Russell or Andrew Moore 1 Announcements PS2 online now Due
More information2D5362 Machine Learning
2D5362 Machine Learning Reinforcement Learning MIT GALib Available at http://lancet.mit.edu/ga/ download galib245.tar.gz gunzip galib245.tar.gz tar xvf galib245.tar cd galib245 make or access my files
More informationCSEP 573: Artificial Intelligence
CSEP 573: Artificial Intelligence Markov Decision Processes (MDP)! Ali Farhadi Many slides over the course adapted from Luke Zettlemoyer, Dan Klein, Pieter Abbeel, Stuart Russell or Andrew Moore 1 Outline
More informationMaking Decisions. CS 3793 Artificial Intelligence Making Decisions 1
Making Decisions CS 3793 Artificial Intelligence Making Decisions 1 Planning under uncertainty should address: The world is nondeterministic. Actions are not certain to succeed. Many events are outside
More informationReinforcement Learning. Slides based on those used in Berkeley's AI class taught by Dan Klein
Reinforcement Learning Slides based on those used in Berkeley's AI class taught by Dan Klein Reinforcement Learning Basic idea: Receive feedback in the form of rewards Agent s utility is defined by the
More information10703 Deep Reinforcement Learning and Control
10703 Deep Reinforcement Learning and Control Russ Salakhutdinov Machine Learning Department rsalakhu@cs.cmu.edu Temporal Difference Learning Used Materials Disclaimer: Much of the material and slides
More information91.420/543: Artificial Intelligence UMass Lowell CS Fall 2010
91.420/543: Artificial Intelligence UMass Lowell CS Fall 2010 Lecture 17 & 18: Markov Decision Processes Oct 12 13, 2010 A subset of Lecture 9 slides from Dan Klein UC Berkeley Many slides over the course
More informationCS 188: Artificial Intelligence
CS 188: Artificial Intelligence Markov Decision Processes Dan Klein, Pieter Abbeel University of California, Berkeley Non-Deterministic Search 1 Example: Grid World A maze-like problem The agent lives
More informationBasic Framework. About this class. Rewards Over Time. [This lecture adapted from Sutton & Barto and Russell & Norvig]
Basic Framework [This lecture adapted from Sutton & Barto and Russell & Norvig] About this class Markov Decision Processes The Bellman Equation Dynamic Programming for finding value functions and optimal
More informationCS 461: Machine Learning Lecture 8
CS 461: Machine Learning Lecture 8 Dr. Kiri Wagstaff kiri.wagstaff@calstatela.edu 2/23/08 CS 461, Winter 2008 1 Plan for Today Review Clustering Reinforcement Learning How different from supervised, unsupervised?
More informationMaking Complex Decisions
Ch. 17 p.1/29 Making Complex Decisions Chapter 17 Ch. 17 p.2/29 Outline Sequential decision problems Value iteration algorithm Policy iteration algorithm Ch. 17 p.3/29 A simple environment 3 +1 p=0.8 2
More informationReinforcement Learning 04 - Monte Carlo. Elena, Xi
Reinforcement Learning 04 - Monte Carlo Elena, Xi Previous lecture 2 Markov Decision Processes Markov decision processes formally describe an environment for reinforcement learning where the environment
More informationCS 234 Winter 2019 Assignment 1 Due: January 23 at 11:59 pm
CS 234 Winter 2019 Assignment 1 Due: January 23 at 11:59 pm For submission instructions please refer to website 1 Optimal Policy for Simple MDP [20 pts] Consider the simple n-state MDP shown in Figure
More informationHow to construct good temporal abstractions. Doina Precup McGill University Joint work with Pierre-Luc Bacon and Jean Mehreb-Harb
How to construct good temporal abstractions Doina Precup McGill University Joint work with Pierre-Luc Bacon and Jean Mehreb-Harb EWRL, December 2016 Options framework Suppose we have an MDP S, A, r, P,
More informationMonte Carlo Methods (Estimators, On-policy/Off-policy Learning)
1 / 24 Monte Carlo Methods (Estimators, On-policy/Off-policy Learning) Julie Nutini MLRG - Winter Term 2 January 24 th, 2017 2 / 24 Monte Carlo Methods Monte Carlo (MC) methods are learning methods, used
More informationCS 188: Artificial Intelligence Fall 2011
CS 188: Artificial Intelligence Fall 2011 Lecture 9: MDPs 9/22/2011 Dan Klein UC Berkeley Many slides over the course adapted from either Stuart Russell or Andrew Moore 2 Grid World The agent lives in
More informationMotivation: disadvantages of MC methods MC does not work for scenarios without termination It updates only at the end of the episode (sometimes - it i
Temporal-Di erence Learning Taras Kucherenko, Joonatan Manttari KTH tarask@kth.se manttari@kth.se March 7, 2017 Taras Kucherenko, Joonatan Manttari (KTH) TD-Learning March 7, 2017 1 / 68 Motivation: disadvantages
More informationMarkov Decision Processes. Lirong Xia
Markov Decision Processes Lirong Xia Today ØMarkov decision processes search with uncertain moves and infinite space ØComputing optimal policy value iteration policy iteration 2 Grid World Ø The agent
More informationAM 121: Intro to Optimization Models and Methods
AM 121: Intro to Optimization Models and Methods Lecture 18: Markov Decision Processes Yiling Chen and David Parkes Lesson Plan Markov decision processes Policies and Value functions Solving: average reward,
More informationThe Option-Critic Architecture
The Option-Critic Architecture Pierre-Luc Bacon, Jean Harb, Doina Precup Reasoning and Learning Lab McGill University, Montreal, Canada AAAI 2017 Intelligence: the ability to generalize and adapt efficiently
More informationLecture 12: MDP1. Victor R. Lesser. CMPSCI 683 Fall 2010
Lecture 12: MDP1 Victor R. Lesser CMPSCI 683 Fall 2010 Biased Random GSAT - WalkSat Notice no random restart 2 Today s lecture Search where there is Uncertainty in Operator Outcome --Sequential Decision
More informationReinforcement Learning
Reinforcement Learning Basic idea: Receive feedback in the form of rewards Agent s utility is defined by the reward function Must (learn to) act so as to maximize expected rewards Grid World The agent
More informationMarkov Decision Processes
Markov Decision Processes Ryan P. Adams COS 324 Elements of Machine Learning Princeton University We now turn to a new aspect of machine learning, in which agents take actions and become active in their
More informationMarkov Decision Processes
Markov Decision Processes Robert Platt Northeastern University Some images and slides are used from: 1. CS188 UC Berkeley 2. AIMA 3. Chris Amato Stochastic domains So far, we have studied search Can use
More informationReinforcement Learning
Reinforcement Learning Monte Carlo Methods Heiko Zimmermann 15.05.2017 1 Monte Carlo Monte Carlo policy evaluation First visit policy evaluation Estimating q values On policy methods Off policy methods
More informationReinforcement Learning. Monte Carlo and Temporal Difference Learning
Reinforcement Learning Monte Carlo and Temporal Difference Learning Manfred Huber 2014 1 Monte Carlo Methods Dynamic Programming Requires complete knowledge of the MDP Spends equal time on each part of
More informationTDT4171 Artificial Intelligence Methods
TDT47 Artificial Intelligence Methods Lecture 7 Making Complex Decisions Norwegian University of Science and Technology Helge Langseth IT-VEST 0 helgel@idi.ntnu.no TDT47 Artificial Intelligence Methods
More information17 MAKING COMPLEX DECISIONS
267 17 MAKING COMPLEX DECISIONS The agent s utility now depends on a sequence of decisions In the following 4 3grid environment the agent makes a decision to move (U, R, D, L) at each time step When the
More informationCPS 270: Artificial Intelligence Markov decision processes, POMDPs
CPS 270: Artificial Intelligence http://www.cs.duke.edu/courses/fall08/cps270/ Markov decision processes, POMDPs Instructor: Vincent Conitzer Warmup: a Markov process with rewards We derive some reward
More informationCS 188: Artificial Intelligence. Outline
C 188: Artificial Intelligence Markov Decision Processes (MDPs) Pieter Abbeel UC Berkeley ome slides adapted from Dan Klein 1 Outline Markov Decision Processes (MDPs) Formalism Value iteration In essence
More informationMulti-step Bootstrapping
Multi-step Bootstrapping Jennifer She Reinforcement Learning: An Introduction by Richard S. Sutton and Andrew G. Barto February 7, 2017 J February 7, 2017 1 / 29 Multi-step Bootstrapping Generalization
More informationApproximate Value Iteration with Temporally Extended Actions (Extended Abstract)
Approximate Value Iteration with Temporally Extended Actions (Extended Abstract) Timothy A. Mann DeepMind, London, UK timothymann@google.com Shie Mannor The Technion, Haifa, Israel shie@ee.technion.ac.il
More informationReinforcement learning and Markov Decision Processes (MDPs) (B) Avrim Blum
Reinforcement learning and Markov Decision Processes (MDPs) 15-859(B) Avrim Blum RL and MDPs General scenario: We are an agent in some state. Have observations, perform actions, get rewards. (See lights,
More informationCS 343: Artificial Intelligence
CS 343: Artificial Intelligence Markov Decision Processes II Prof. Scott Niekum The University of Texas at Austin [These slides based on those of Dan Klein and Pieter Abbeel for CS188 Intro to AI at UC
More informationCS 360: Advanced Artificial Intelligence Class #16: Reinforcement Learning
CS 360: Advanced Artificial Intelligence Class #16: Reinforcement Learning Daniel M. Gaines Note: content for slides adapted from Sutton and Barto [1998] Introduction Animals learn through interaction
More informationSequential Coalition Formation for Uncertain Environments
Sequential Coalition Formation for Uncertain Environments Hosam Hanna Computer Sciences Department GREYC - University of Caen 14032 Caen - France hanna@info.unicaen.fr Abstract In several applications,
More informationMarkov Decision Processes (MDPs) CS 486/686 Introduction to AI University of Waterloo
Markov Decision Processes (MDPs) CS 486/686 Introduction to AI University of Waterloo Outline Sequential Decision Processes Markov chains Highlight Markov property Discounted rewards Value iteration Markov
More informationPolicy Iteration for Learning an Exercise Policy for American Options
Policy Iteration for Learning an Exercise Policy for American Options Yuxi Li, Dale Schuurmans Department of Computing Science, University of Alberta Abstract. Options are important financial instruments,
More informationLecture 4: Model-Free Prediction
Lecture 4: Model-Free Prediction David Silver Outline 1 Introduction 2 Monte-Carlo Learning 3 Temporal-Difference Learning 4 TD(λ) Introduction Model-Free Reinforcement Learning Last lecture: Planning
More informationThe exam is closed book, closed calculator, and closed notes except your one-page crib sheet.
CS 188 Spring 2015 Introduction to Artificial Intelligence Midterm 1 You have approximately 2 hours and 50 minutes. The exam is closed book, closed calculator, and closed notes except your one-page crib
More informationElif Özge Özdamar T Reinforcement Learning - Theory and Applications February 14, 2006
On the convergence of Q-learning Elif Özge Özdamar elif.ozdamar@helsinki.fi T-61.6020 Reinforcement Learning - Theory and Applications February 14, 2006 the covergence of stochastic iterative algorithms
More informationMarkov Decision Process
Markov Decision Process Human-aware Robotics 2018/02/13 Chapter 17.3 in R&N 3rd Ø Announcement: q Slides for this lecture are here: http://www.public.asu.edu/~yzhan442/teaching/cse471/lectures/mdp-ii.pdf
More informationLearning Exercise Policies for American Options
Yuxi Li Dept. of Computing Science University of Alberta Edmonton, Alberta Canada T6G 2E8 Csaba Szepesvari Dept. of Computing Science University of Alberta Edmonton, Alberta Canada T6G 2E8 Dale Schuurmans
More informationQ1. [?? pts] Search Traces
CS 188 Spring 2010 Introduction to Artificial Intelligence Midterm Exam Solutions Q1. [?? pts] Search Traces Each of the trees (G1 through G5) was generated by searching the graph (below, left) with a
More informationCS 188: Artificial Intelligence
CS 188: Artificial Intelligence Markov Decision Processes Dan Klein, Pieter Abbeel University of California, Berkeley Non Deterministic Search Example: Grid World A maze like problem The agent lives in
More informationIterative Hierarchical Optimization for Misspecified Problems
Iterative Hierarchical Optimization for Misspecified Problems Daniel J. Mankowitz 1 Timothy A. Mann 2 Shie Mannor 1 danielm@tx.technion.ac.il timothymann@google.com shie@@ee.technion.ac.il Abstract For
More informationChapter 6: Temporal Difference Learning
Chapter 6: emporal Difference Learning Objectives of this chapter: Introduce emporal Difference (D) learning Focus first on policy evaluation, or prediction, methods hen extend to control methods by following
More informationReinforcement Learning
Reinforcement Learning n-step bootstrapping Daniel Hennes 12.06.2017 University Stuttgart - IPVS - Machine Learning & Robotics 1 n-step bootstrapping Unifying Monte Carlo and TD n-step TD n-step Sarsa
More informationLecture 2: Making Good Sequences of Decisions Given a Model of World. CS234: RL Emma Brunskill Winter 2018
Lecture 2: Making Good Sequences of Decisions Given a Model of World CS234: RL Emma Brunskill Winter 218 Human in the loop exoskeleton work from Steve Collins lab Class Structure Last Time: Introduction
More informationPatrolling in A Stochastic Environment
Patrolling in A Stochastic Environment Student Paper Submission (Suggested Track: Modeling and Simulation) Sui Ruan 1 (Student) E-mail: sruan@engr.uconn.edu Candra Meirina 1 (Student) E-mail: meirina@engr.uconn.edu
More informationA Laplacian Framework for Option Discovery in Reinforcement Learning
Marlos C. Machado 1 Marc G. Bellemare 2 Michael Bowling 1 Abstract Representation learning and option discovery are two of the biggest challenges in reinforcement learning (RL). Proto-value functions (PVFs)
More informationCOS402- Artificial Intelligence Fall Lecture 17: MDP: Value Iteration and Policy Iteration
COS402- Artificial Intelligence Fall 2015 Lecture 17: MDP: Value Iteration and Policy Iteration Outline The Bellman equation and Bellman update Contraction Value iteration Policy iteration The Bellman
More informationCOMP417 Introduction to Robotics and Intelligent Systems. Reinforcement Learning - 2
COMP417 Introduction to Robotics and Intelligent Systems Reinforcement Learning - 2 Speaker: Sandeep Manjanna Acklowledgement: These slides use material from Pieter Abbeel s, Dan Klein s and John Schulman
More informationCompound Reinforcement Learning: Theory and An Application to Finance
Compound Reinforcement Learning: Theory and An Application to Finance Tohgoroh Matsui 1, Takashi Goto 2, Kiyoshi Izumi 3,4, and Yu Chen 3 1 Chubu University, 1200 Matsumoto-cho, Kasugai, 487-8501 Aichi,
More informationEnergy Storage Arbitrage in Real-Time Markets via Reinforcement Learning
Energy Storage Arbitrage in Real-Time Markets via Reinforcement Learning Hao Wang, Baosen Zhang Department of Electrical Engineering, University of Washington, Seattle, WA 9895 Email: {hwang6,zhangbao}@uw.edu
More informationReinforcement Learning
Reinforcement Learning Model-based RL and Integrated Learning-Planning Planning and Search, Model Learning, Dyna Architecture, Exploration-Exploitation (many slides from lectures of Marc Toussaint & David
More informationRegret Minimization in MDPs with Options without Prior Knowledge
Ronan Fruit Matteo Pirotta Alessandro Lazaric Emma Brunskill 2. Introduction Learning how to make good decisions in complex domains almost always requires some form of hierarchical reasoning. One powerful
More informationScenario reduction and scenario tree construction for power management problems
Scenario reduction and scenario tree construction for power management problems N. Gröwe-Kuska, H. Heitsch and W. Römisch Humboldt-University Berlin Institute of Mathematics Page 1 of 20 IEEE Bologna POWER
More informationMarkov Decision Processes
Markov Decision Processes Robert Platt Northeastern University Some images and slides are used from: 1. CS188 UC Berkeley 2. RN, AIMA Stochastic domains Image: Berkeley CS188 course notes (downloaded Summer
More informationOptimal Policies for Distributed Data Aggregation in Wireless Sensor Networks
Optimal Policies for Distributed Data Aggregation in Wireless Sensor Networks Hussein Abouzeid Department of Electrical Computer and Systems Engineering Rensselaer Polytechnic Institute abouzeid@ecse.rpi.edu
More informationLong Term Values in MDPs Second Workshop on Open Games
A (Co)Algebraic Perspective on Long Term Values in MDPs Second Workshop on Open Games Helle Hvid Hansen Delft University of Technology Helle Hvid Hansen (TU Delft) 2nd WS Open Games Oxford 4-6 July 2018
More informationEnsemble Methods for Reinforcement Learning with Function Approximation
Ensemble Methods for Reinforcement Learning with Function Approximation Stefan Faußer and Friedhelm Schwenker Institute of Neural Information Processing, University of Ulm, 89069 Ulm, Germany {stefan.fausser,friedhelm.schwenker}@uni-ulm.de
More informationc 2004 IEEE. Reprinted from the Proceedings of the International Joint Conference on Neural Networks (IJCNN-2004), Budapest, Hungary, pp
c 24 IEEE. Reprinted from the Proceedings of the International Joint Conference on Neural Networks (IJCNN-24), Budapest, Hungary, pp. 197 112. This material is posted here with permission of the IEEE.
More informationLong-Term Values in MDPs, Corecursively
Long-Term Values in MDPs, Corecursively Applied Category Theory, 15-16 March 2018, NIST Helle Hvid Hansen Delft University of Technology Helle Hvid Hansen (TU Delft) MDPs, Corecursively NIST, 15/Mar/2018
More informationCS 188 Fall Introduction to Artificial Intelligence Midterm 1. ˆ You have approximately 2 hours and 50 minutes.
CS 188 Fall 2013 Introduction to Artificial Intelligence Midterm 1 ˆ You have approximately 2 hours and 50 minutes. ˆ The exam is closed book, closed notes except your one-page crib sheet. ˆ Please use
More informationDynamic Portfolio Choice II
Dynamic Portfolio Choice II Dynamic Programming Leonid Kogan MIT, Sloan 15.450, Fall 2010 c Leonid Kogan ( MIT, Sloan ) Dynamic Portfolio Choice II 15.450, Fall 2010 1 / 35 Outline 1 Introduction to Dynamic
More informationLecture 7: Bayesian approach to MAB - Gittins index
Advanced Topics in Machine Learning and Algorithmic Game Theory Lecture 7: Bayesian approach to MAB - Gittins index Lecturer: Yishay Mansour Scribe: Mariano Schain 7.1 Introduction In the Bayesian approach
More informationRegret Minimization in MDPs with Options without Prior Knowledge
Regret Minimization in MDPs with Options without Prior Knowledge Ronan Fruit Sequel Team - Inria Lille ronan.fruit@inria.fr Alessandro Lazaric Sequel Team - Inria Lille alessandro.lazaric@inria.fr Matteo
More informationAn Algorithm for Trading and Portfolio Management Using. strategy. Since this type of trading system is optimized
pp 83-837,. An Algorithm for Trading and Portfolio Management Using Q-learning and Sharpe Ratio Maximization Xiu Gao Department of Computer Science and Engineering The Chinese University of HongKong Shatin,
More informationLogistics. CS 473: Artificial Intelligence. Markov Decision Processes. PS 2 due today Midterm in one week
CS 473: Artificial Intelligence Markov Decision Processes Dan Weld University of Washington [Slides originally created by Dan Klein & Pieter Abbeel for CS188 Intro to AI at UC Berkeley. All CS188 materials
More informationLecture 1: Lucas Model and Asset Pricing
Lecture 1: Lucas Model and Asset Pricing Economics 714, Spring 2018 1 Asset Pricing 1.1 Lucas (1978) Asset Pricing Model We assume that there are a large number of identical agents, modeled as a representative
More informationReasoning with Uncertainty
Reasoning with Uncertainty Markov Decision Models Manfred Huber 2015 1 Markov Decision Process Models Markov models represent the behavior of a random process, including its internal state and the externally
More informationCS 188 Fall Introduction to Artificial Intelligence Midterm 1. ˆ You have approximately 2 hours and 50 minutes.
CS 188 Fall 2013 Introduction to Artificial Intelligence Midterm 1 ˆ You have approximately 2 hours and 50 minutes. ˆ The exam is closed book, closed notes except your one-page crib sheet. ˆ Please use
More informationMonte-Carlo Planning Look Ahead Trees. Alan Fern
Monte-Carlo Planning Look Ahead Trees Alan Fern 1 Monte-Carlo Planning Outline Single State Case (multi-armed bandits) A basic tool for other algorithms Monte-Carlo Policy Improvement Policy rollout Policy
More information