Q-Learning and Stochastic Approximation
|
|
- Johnathan Stewart
- 5 years ago
- Views:
Transcription
1 MS&E338 Reinforcement Learning Lecture Q-Learning and Stochastic Approximation Lecturer: Ben Van Roy Scribe: Christopher Lazarus Javier Sagastuy In this lecture we study the convergence of Q-Learning updates via stochastic approximation results. 1 Q-learning update Assume we are given data samples of the following form: s, a, r +1, s +1 = 0, 1,,... and we iteratively apply the following update to the state-action value function: { 1 γ Q s, a + γ r +1 + max a Q +1 s, a = A Q s +1, a if s = s, a = a 1 Q s, a otherwise Proposition 1. If each s, a S A is sampled infinitely often and we have {γ } deterministic satisfying s, a γ =, γ <, then Q Q :s,a =s,a :s,a =s,a Originally, in class, there were a couple of issues with the formulation of the above proposition: we want each state-action pair to be sampled infinitely often. If an adversary is deciding that, it can try to game the system to just choose an update at particular times, for example: Adversary pics particular state action pairs when γ is zero. Adversary spaces updates, so that spaces get bigger and bigger and it can loo as though the values for gamma are plummeting quicly. We can rewrite the updating equation as temporal difference {}} { Q +1 s, a = Q s, a + γ r +1 + max Q s +1, a Q s, a a A A temporal difference is a difference between predictions that you can mae in consecutive time periods. It is composed of two parts: the current value of the state-action function and the proposed value by the greedy update to the Q function. The difference helps us realize if we over or underestimated the previous value of the Q function. ote that the Q-learning update can be understood as an asynchronous version of stochastic approximation to value iteration. Thus, in the following section we study Stochastic Approximation as a way to understand the convergence properties of Q-Learning. Stochastic Approximation We are not going to learn a comprehensive foundation to prove stochastic approximation results. We will go over intuition for how formal analysis of these things goes. The idea to stochastic approximation is: 1
2 x +1 = x + γ sx, w where w is a random disturbance. Let s assume that w is ergodic and in particular there is some stationary distribution for w so we can tal about expectation and distribution. In fact, if w is drawn form the steady state distribution, let sx = E [sx, w ] Under various technical conditions when γ is small the sequence approximates an ODE of the form x t = sx t The idea is that we want a relationship from a continuous to a discrete sequence. continuous {}}{ x t t discrete {}}{ x 1 γ i The γ is can be thought of lie the dt in an ODE. x t+dt x t = sx t dt x t+dt = x t + dt sx t If γ =, γ < then we would converge with this update rule. As increases, this follows more and more closely the tracs of the ODE. Let s loo at a simple case: assume the sample mean of w i.i.d. with E [ w] < x = 1 1 w i x +1 = 1 x +1 = w i = 1 w x approximately, using the LL x w = 1 γ x + γ w if we let γ = 1 By the law of large numbers, x E[w 0 ]. In fact, as long as γ = and γ <, we get x E[w 0 ]..1 Understanding the intuition behind the ODE approximation We now reason about the same example in a continuous context. Let h be a small increment in the continuous time domain. x t+h = x t + hsx t, w t
3 Suppose large but << 1 so that h << 1. Then, h 1 x t+h = x t + h sx t+nh, w t+nh 1 x t + h sx t, w t+nh = x t + h = x t + dt dt 1 1 sx t + O sx t, w t+nh 1 from equation by induction we assume that x t doesn t change much since nh is small multiplying and dividing by 1 where in the last step, O comes from the fact that the variance of the mean of iid samples is on the order of 1. We will leverage basic martingale convergence theorems and use that to prove how basic stochastic approximation theorems wor.. A prototypical example of a stochastic approximation result Proposition. If w i.i.d, and there exist x, c 1, c such that for all x 1. x x sx c 1 x x. E [ sx, w ] c 1 + x x and if γ is deterministic with γ =, γ <, then we have x x with probability 1. Intuitively, the two necessary conditions in proposition can be thought as follows: 1. States that you are going in the right direction fast enough.. Gives a bound on the noise provided by w. It may be very noisy, but not too much. If you are far away you are allowed large noise cause that is compensated by the fact that you can tae big steps. Theorem 1. Supermartingale Convergence Theorem Let X, Y, Z = 0, 1,,... be nonnegative scalar random variables, with Y <. If E [X +1 ] X + Y Z then with probability 1, lim X exists and is finite, and Z <. In the above statement, the sub on the expectation means conditioning on X 0,..., X. ote that the result presented in Theorem 1 is a stochastic generalization of convergence in real analysis. We are not going to prove Theorem 1, it is pretty hard, but we will use it to prove proposition : 3
4 Proof. Let = x x then +1 = x + γ sx, w x = + γ sx, w γ x x sx, w E [ +1 ] + γc 1 + x x γ c 1 x x from the necessary conditions on prop. = + γ c 1 + γ c 1 = + c γ c 1 γ X E [X +1 ] X + Y Z Z + c γ Y We now want to see if the variables we just defined satisfy the conditions on Theorem 1. First, note that Y = c γ < since γ <. Also, X and Y as defined are non-negative. However, note that Z = C 1 γ C γ could tae on negative values. But since γ converges to 0, there will be some K such that K, Z 0. Thus, we can loo at Z starting at index = K. ow, from Theorem 1 we now that X = = x x converges to a finite random variable with probability 1. We also now that Z <. Since Z = c γ c 1 γ < and we now that c γ <, then c 1 γ <. However, since c 1 is a constant and γ =, the only way the previous sum could tae on a finite value is if is converging to zero. If converged to any value other than zero, the sum would not converge. ow we finally now that = x x 0 with probability 1, which implies that x x with probability 1, as desired. Example 1. Consider F : R R s.t F x F y α x y, α 0, 1 with w i.i.d. E [w ] = 0, E [ w ] <. Then: 1. x +1 = x + γ F x x + w sx, w = F x x + w sx = F x x x = F x x x sx = x x F x x + x x x x x x x x F x x + x x α x x + x x = 1 α x x 4
5 . [ ] E sx, w [ = E F x x + w E [ F x x + w ] E [1 + α x x + w ] [ ] E 1 + α x x + w [ ] 1 + α 1 + E w C ] 1 + x x Thus, by Proposition, x x. One last problem to thin about: in the last homewor assignment we showed that asynchronous Value Iteration converges to the optimal value function. ow, what if instead of having a maximum norm contraction mapping, we had a contraction with respect to the euclidean norm? We can show that this does not guarantee convergence with an asynchronous update although you do get it in the synchronous case. Come up with an example that there is an asynchronous process that does not get you to the fixed point with the euclidean contraction. Homewor # Let T : R R be such that α 0, 1 s.t. V, V, update V +1 = { T V s if s = s V s otherwise T V T V α V V. Consider the Show that V may not converge to V even if each s S is selected infinitely often. References [1] John Tsitsilis. Asynchronous stochastic approximation and q-learning. Machine learning, 163:185 0,
Algorithms for MDPs and Their Convergence
MS&E338 Reinforcement Learning Lecture 2 - April 4 208 Algorithms for MDPs and Their Convergence Lecturer: Ben Van Roy Scribe: Matthew Creme and Kristen Kessel Bellman operators Recall from last lecture
More informationQ-Learning and Enhanced Policy Iteration in Discounted Dynamic Programming
MATHEMATICS OF OPERATIONS RESEARCH Vol. 37, No. 1, February 2012, pp. 66 94 ISSN 0364-765X (print) ISSN 1526-5471 (online) http://dx.doi.org/10.1287/moor.1110.0532 2012 INFORMS Q-Learning and Enhanced
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 informationMS&E338 Reinforcement Learning Lecture 1 - April 2, Introduction
MS&E338 Reinforcement Learning Lecture 1 - April 2, 2018 Introduction Lecturer: Ben Van Roy Scribe: Gabriel Maher 1 Reinforcement Learning Introduction In reinforcement learning (RL) we consider an agent
More informationQ-Learning for Markov Decision Processes*
McGill University ECSE 506: Term Project Q-Learning for Markov Decision Processes* Authors: Khoa Phan khoa.phan@mail.mcgill.ca Sandeep Manjanna sandeep.manjanna@mail.mcgill.ca (*Based on: Convergence of
More informationGradient Estimation for Attractor Networks
Gradient Estimation for Attractor Networks Thomas Flynn Department of Computer Science Graduate Center of CUNY July 2017 1 Outline Motivations Deterministic attractor networks Stochastic attractor networks
More information11. Further Issues in Using OLS with TS Data
11. Further Issues in Using OLS with TS Data With TS, including lags of the dependent variable often allow us to fit much better the variation in y Exact distribution theory is rarely available in TS applications,
More informationDependence and independence
Roberto s Notes on Linear Algebra Chapter 7: Subspaces Section 1 Dependence and independence What you need to now already: Basic facts and operations involving Euclidean vectors. Matrices determinants
More informationTechnical Details about the Expectation Maximization (EM) Algorithm
Technical Details about the Expectation Maximization (EM Algorithm Dawen Liang Columbia University dliang@ee.columbia.edu February 25, 2015 1 Introduction Maximum Lielihood Estimation (MLE is widely used
More informationA Gentle Introduction to Reinforcement Learning
A Gentle Introduction to Reinforcement Learning Alexander Jung 2018 1 Introduction and Motivation Consider the cleaning robot Rumba which has to clean the office room B329. In order to keep things simple,
More informationMarkov Decision Processes and Dynamic Programming
Markov Decision Processes and Dynamic Programming A. LAZARIC (SequeL Team @INRIA-Lille) ENS Cachan - Master 2 MVA SequeL INRIA Lille MVA-RL Course How to model an RL problem The Markov Decision Process
More informationLinear stochastic approximation driven by slowly varying Markov chains
Available online at www.sciencedirect.com Systems & Control Letters 50 2003 95 102 www.elsevier.com/locate/sysconle Linear stochastic approximation driven by slowly varying Marov chains Viay R. Konda,
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 informationOn the Convergence of Optimistic Policy Iteration
Journal of Machine Learning Research 3 (2002) 59 72 Submitted 10/01; Published 7/02 On the Convergence of Optimistic Policy Iteration John N. Tsitsiklis LIDS, Room 35-209 Massachusetts Institute of Technology
More informationNon-Convex Optimization. CS6787 Lecture 7 Fall 2017
Non-Convex Optimization CS6787 Lecture 7 Fall 2017 First some words about grading I sent out a bunch of grades on the course management system Everyone should have all their grades in Not including paper
More informationNotes on Discrete Probability
Columbia University Handout 3 W4231: Analysis of Algorithms September 21, 1999 Professor Luca Trevisan Notes on Discrete Probability The following notes cover, mostly without proofs, the basic notions
More informationMarkov Decision Processes and Dynamic Programming
Markov Decision Processes and Dynamic Programming A. LAZARIC (SequeL Team @INRIA-Lille) Ecole Centrale - Option DAD SequeL INRIA Lille EC-RL Course In This Lecture A. LAZARIC Markov Decision Processes
More informationZEROES OF INTEGER LINEAR RECURRENCES. 1. Introduction. 4 ( )( 2 1) n
ZEROES OF INTEGER LINEAR RECURRENCES DANIEL LITT Consider the integer linear recurrence 1. Introduction x n = x n 1 + 2x n 2 + 3x n 3 with x 0 = x 1 = x 2 = 1. For which n is x n = 0? Answer: x n is never
More informationECE521 week 3: 23/26 January 2017
ECE521 week 3: 23/26 January 2017 Outline Probabilistic interpretation of linear regression - Maximum likelihood estimation (MLE) - Maximum a posteriori (MAP) estimation Bias-variance trade-off Linear
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 informationBindel, Fall 2013 Matrix Computations (CS 6210) Week 2: Friday, Sep 6
Order notation Wee 2: Friday, Sep 6 We ll use order notation in multiple ways this semester, so we briefly review it here. This should be familiar to many of you. We say f(n) = O(g(n)) (read f(n) is big-o
More informationInternet Monetization
Internet Monetization March May, 2013 Discrete time Finite A decision process (MDP) is reward process with decisions. It models an environment in which all states are and time is divided into stages. Definition
More informationIFT Lecture 6 Nesterov s Accelerated Gradient, Stochastic Gradient Descent
IFT 6085 - Lecture 6 Nesterov s Accelerated Gradient, Stochastic Gradient Descent This version of the notes has not yet been thoroughly checked. Please report any bugs to the scribes or instructor. Scribe(s):
More informationCSC 2541: Bayesian Methods for Machine Learning
CSC 2541: Bayesian Methods for Machine Learning Radford M. Neal, University of Toronto, 2011 Lecture 3 More Markov Chain Monte Carlo Methods The Metropolis algorithm isn t the only way to do MCMC. We ll
More informationLecture 3 Stationary Processes and the Ergodic LLN (Reference Section 2.2, Hayashi)
Lecture 3 Stationary Processes and the Ergodic LLN (Reference Section 2.2, Hayashi) Our immediate goal is to formulate an LLN and a CLT which can be applied to establish sufficient conditions for the consistency
More informationRecent Advances in SPSA at the Extremes: Adaptive Methods for Smooth Problems and Discrete Methods for Non-Smooth Problems
Recent Advances in SPSA at the Extremes: Adaptive Methods for Smooth Problems and Discrete Methods for Non-Smooth Problems SGM2014: Stochastic Gradient Methods IPAM, February 24 28, 2014 James C. Spall
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 informationIntroduction: The Perceptron
Introduction: The Perceptron Haim Sompolinsy, MIT October 4, 203 Perceptron Architecture The simplest type of perceptron has a single layer of weights connecting the inputs and output. Formally, the perceptron
More informationWeighted Majority and the Online Learning Approach
Statistical Techniques in Robotics (16-81, F12) Lecture#9 (Wednesday September 26) Weighted Majority and the Online Learning Approach Lecturer: Drew Bagnell Scribe:Narek Melik-Barkhudarov 1 Figure 1: Drew
More informationEE 381V: Large Scale Optimization Fall Lecture 24 April 11
EE 381V: Large Scale Optimization Fall 2012 Lecture 24 April 11 Lecturer: Caramanis & Sanghavi Scribe: Tao Huang 24.1 Review In past classes, we studied the problem of sparsity. Sparsity problem is that
More informationLecture 4: Introduction to stochastic processes and stochastic calculus
Lecture 4: Introduction to stochastic processes and stochastic calculus Cédric Archambeau Centre for Computational Statistics and Machine Learning Department of Computer Science University College London
More informationEconomics 2010c: Lectures 9-10 Bellman Equation in Continuous Time
Economics 2010c: Lectures 9-10 Bellman Equation in Continuous Time David Laibson 9/30/2014 Outline Lectures 9-10: 9.1 Continuous-time Bellman Equation 9.2 Application: Merton s Problem 9.3 Application:
More informationSimple Techniques for Improving SGD. CS6787 Lecture 2 Fall 2017
Simple Techniques for Improving SGD CS6787 Lecture 2 Fall 2017 Step Sizes and Convergence Where we left off Stochastic gradient descent x t+1 = x t rf(x t ; yĩt ) Much faster per iteration than gradient
More informationOpen Economy Macroeconomics: Theory, methods and applications
Open Economy Macroeconomics: Theory, methods and applications Lecture 4: The state space representation and the Kalman Filter Hernán D. Seoane UC3M January, 2016 Today s lecture State space representation
More informationApproximate Dynamic Programming
Approximate Dynamic Programming A. LAZARIC (SequeL Team @INRIA-Lille) Ecole Centrale - Option DAD SequeL INRIA Lille EC-RL Course Value Iteration: the Idea 1. Let V 0 be any vector in R N A. LAZARIC Reinforcement
More informationLecture 5 Linear Quadratic Stochastic Control
EE363 Winter 2008-09 Lecture 5 Linear Quadratic Stochastic Control linear-quadratic stochastic control problem solution via dynamic programming 5 1 Linear stochastic system linear dynamical system, over
More informationLecture 16: Introduction to Neural Networks
Lecture 16: Introduction to Neural Networs Instructor: Aditya Bhasara Scribe: Philippe David CS 5966/6966: Theory of Machine Learning March 20 th, 2017 Abstract In this lecture, we consider Bacpropagation,
More informationExponential Moving Average Based Multiagent Reinforcement Learning Algorithms
Exponential Moving Average Based Multiagent Reinforcement Learning Algorithms Mostafa D. Awheda Department of Systems and Computer Engineering Carleton University Ottawa, Canada KS 5B6 Email: mawheda@sce.carleton.ca
More information6 Reinforcement Learning
6 Reinforcement Learning As discussed above, a basic form of supervised learning is function approximation, relating input vectors to output vectors, or, more generally, finding density functions p(y,
More informationOptimal Stopping Problems
2.997 Decision Making in Large Scale Systems March 3 MIT, Spring 2004 Handout #9 Lecture Note 5 Optimal Stopping Problems In the last lecture, we have analyzed the behavior of T D(λ) for approximating
More informationModule 9: Stationary Processes
Module 9: Stationary Processes Lecture 1 Stationary Processes 1 Introduction A stationary process is a stochastic process whose joint probability distribution does not change when shifted in time or space.
More informationBandit Algorithms. Zhifeng Wang ... Department of Statistics Florida State University
Bandit Algorithms Zhifeng Wang Department of Statistics Florida State University Outline Multi-Armed Bandits (MAB) Exploration-First Epsilon-Greedy Softmax UCB Thompson Sampling Adversarial Bandits Exp3
More informationOptimization and Gradient Descent
Optimization and Gradient Descent INFO-4604, Applied Machine Learning University of Colorado Boulder September 12, 2017 Prof. Michael Paul Prediction Functions Remember: a prediction function is the function
More informationMachine Learning and Bayesian Inference. Unsupervised learning. Can we find regularity in data without the aid of labels?
Machine Learning and Bayesian Inference Dr Sean Holden Computer Laboratory, Room FC6 Telephone extension 6372 Email: sbh11@cl.cam.ac.uk www.cl.cam.ac.uk/ sbh11/ Unsupervised learning Can we find regularity
More informationThe Art of Sequential Optimization via Simulations
The Art of Sequential Optimization via Simulations Stochastic Systems and Learning Laboratory EE, CS* & ISE* Departments Viterbi School of Engineering University of Southern California (Based on joint
More informationSome Review Problems for Exam 3: Solutions
Math 3355 Fall 018 Some Review Problems for Exam 3: Solutions I thought I d start by reviewing some counting formulas. Counting the Complement: Given a set U (the universe for the problem), if you want
More informationSolutions to Homework 2
Solutions to Homewor Due Tuesday, July 6,. Chapter. Problem solution. If the series for ln+z and ln z both converge, +z then we can find the series for ln z by term-by-term subtraction of the two series:
More information1 Markov decision processes
2.997 Decision-Making in Large-Scale Systems February 4 MI, Spring 2004 Handout #1 Lecture Note 1 1 Markov decision processes In this class we will study discrete-time stochastic systems. We can describe
More informationAn Empirical Algorithm for Relative Value Iteration for Average-cost MDPs
2015 IEEE 54th Annual Conference on Decision and Control CDC December 15-18, 2015. Osaka, Japan An Empirical Algorithm for Relative Value Iteration for Average-cost MDPs Abhishek Gupta Rahul Jain Peter
More informationPlayers as Serial or Parallel Random Access Machines. Timothy Van Zandt. INSEAD (France)
Timothy Van Zandt Players as Serial or Parallel Random Access Machines DIMACS 31 January 2005 1 Players as Serial or Parallel Random Access Machines (EXPLORATORY REMARKS) Timothy Van Zandt tvz@insead.edu
More informationCS 287: Advanced Robotics Fall Lecture 14: Reinforcement Learning with Function Approximation and TD Gammon case study
CS 287: Advanced Robotics Fall 2009 Lecture 14: Reinforcement Learning with Function Approximation and TD Gammon case study Pieter Abbeel UC Berkeley EECS Assignment #1 Roll-out: nice example paper: X.
More informationNotice that lemma 4 has nothing to do with 3-colorability. To obtain a better result for 3-colorable graphs, we need the following observation.
COMPSCI 632: Approximation Algorithms November 1, 2017 Lecturer: Debmalya Panigrahi Lecture 18 Scribe: Feng Gui 1 Overview In this lecture, we examine graph coloring algorithms. We first briefly discuss
More informationAbel Summation MOP 2007, Black Group
Abel Summation MOP 007, Blac Group Zachary Abel June 5, 007 This lecture focuses on the Abel Summation formula, which is most often useful as a way to tae advantage of unusual given conditions such as
More informationFor those who want to skip this chapter and carry on, that s fine, all you really need to know is that for the scalar expression: 2 H
1 Matrices are rectangular arrays of numbers. hey are usually written in terms of a capital bold letter, for example A. In previous chapters we ve looed at matrix algebra and matrix arithmetic. Where things
More informationCONTROL SYSTEMS, ROBOTICS AND AUTOMATION Vol. XI Stochastic Stability - H.J. Kushner
STOCHASTIC STABILITY H.J. Kushner Applied Mathematics, Brown University, Providence, RI, USA. Keywords: stability, stochastic stability, random perturbations, Markov systems, robustness, perturbed systems,
More informationBayesian Machine Learning
Bayesian Machine Learning Andrew Gordon Wilson ORIE 6741 Lecture 2: Bayesian Basics https://people.orie.cornell.edu/andrew/orie6741 Cornell University August 25, 2016 1 / 17 Canonical Machine Learning
More informationCS168: The Modern Algorithmic Toolbox Lecture #8: How PCA Works
CS68: The Modern Algorithmic Toolbox Lecture #8: How PCA Works Tim Roughgarden & Gregory Valiant April 20, 206 Introduction Last lecture introduced the idea of principal components analysis (PCA). The
More informationOrdinary Least Squares Linear Regression
Ordinary Least Squares Linear Regression Ryan P. Adams COS 324 Elements of Machine Learning Princeton University Linear regression is one of the simplest and most fundamental modeling ideas in statistics
More information, and rewards and transition matrices as shown below:
CSE 50a. Assignment 7 Out: Tue Nov Due: Thu Dec Reading: Sutton & Barto, Chapters -. 7. Policy improvement Consider the Markov decision process (MDP) with two states s {0, }, two actions a {0, }, discount
More informationarxiv: v3 [math.oc] 8 Jan 2019
Why Random Reshuffling Beats Stochastic Gradient Descent Mert Gürbüzbalaban, Asuman Ozdaglar, Pablo Parrilo arxiv:1510.08560v3 [math.oc] 8 Jan 2019 January 9, 2019 Abstract We analyze the convergence rate
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 informationReinforcement Learning. Introduction
Reinforcement Learning Introduction Reinforcement Learning Agent interacts and learns from a stochastic environment Science of sequential decision making Many faces of reinforcement learning Optimal control
More information17 Solution of Nonlinear Systems
17 Solution of Nonlinear Systems We now discuss the solution of systems of nonlinear equations. An important ingredient will be the multivariate Taylor theorem. Theorem 17.1 Let D = {x 1, x 2,..., x m
More informationDiscrete Mathematics and Probability Theory Spring 2016 Rao and Walrand Note 14
CS 70 Discrete Mathematics and Probability Theory Spring 2016 Rao and Walrand Note 14 Introduction One of the key properties of coin flips is independence: if you flip a fair coin ten times and get ten
More informationPrioritized Sweeping Converges to the Optimal Value Function
Technical Report DCS-TR-631 Prioritized Sweeping Converges to the Optimal Value Function Lihong Li and Michael L. Littman {lihong,mlittman}@cs.rutgers.edu RL 3 Laboratory Department of Computer Science
More informationTheorem (Special Case of Ramsey s Theorem) R(k, l) is finite. Furthermore, it satisfies,
Math 16A Notes, Wee 6 Scribe: Jesse Benavides Disclaimer: These notes are not nearly as polished (and quite possibly not nearly as correct) as a published paper. Please use them at your own ris. 1. Ramsey
More informationCOMS 4721: Machine Learning for Data Science Lecture 10, 2/21/2017
COMS 4721: Machine Learning for Data Science Lecture 10, 2/21/2017 Prof. John Paisley Department of Electrical Engineering & Data Science Institute Columbia University FEATURE EXPANSIONS FEATURE EXPANSIONS
More informationLecture 1: Brief Review on Stochastic Processes
Lecture 1: Brief Review on Stochastic Processes A stochastic process is a collection of random variables {X t (s) : t T, s S}, where T is some index set and S is the common sample space of the random variables.
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 information1 The independent set problem
ORF 523 Lecture 11 Spring 2016, Princeton University Instructor: A.A. Ahmadi Scribe: G. Hall Tuesday, March 29, 2016 When in doubt on the accuracy of these notes, please cross chec with the instructor
More informationA Convergent O(n) Algorithm for Off-policy Temporal-difference Learning with Linear Function Approximation
A Convergent O(n) Algorithm for Off-policy Temporal-difference Learning with Linear Function Approximation Richard S. Sutton, Csaba Szepesvári, Hamid Reza Maei Reinforcement Learning and Artificial Intelligence
More information0.1 Motivating example: weighted majority algorithm
princeton univ. F 16 cos 521: Advanced Algorithm Design Lecture 8: Decision-making under total uncertainty: the multiplicative weight algorithm Lecturer: Sanjeev Arora Scribe: Sanjeev Arora (Today s notes
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 informationMachine Learning and Data Mining. Linear regression. Kalev Kask
Machine Learning and Data Mining Linear regression Kalev Kask Supervised learning Notation Features x Targets y Predictions ŷ Parameters q Learning algorithm Program ( Learner ) Change q Improve performance
More informationStochastic bandits: Explore-First and UCB
CSE599s, Spring 2014, Online Learning Lecture 15-2/19/2014 Stochastic bandits: Explore-First and UCB Lecturer: Brendan McMahan or Ofer Dekel Scribe: Javad Hosseini In this lecture, we like to answer this
More informationReinforcement Learning and Optimal Control. ASU, CSE 691, Winter 2019
Reinforcement Learning and Optimal Control ASU, CSE 691, Winter 2019 Dimitri P. Bertsekas dimitrib@mit.edu Lecture 8 Bertsekas Reinforcement Learning 1 / 21 Outline 1 Review of Infinite Horizon Problems
More informationLecture 2. We now introduce some fundamental tools in martingale theory, which are useful in controlling the fluctuation of martingales.
Lecture 2 1 Martingales We now introduce some fundamental tools in martingale theory, which are useful in controlling the fluctuation of martingales. 1.1 Doob s inequality We have the following maximal
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 informationReinforcement Learning
Reinforcement Learning March May, 2013 Schedule Update Introduction 03/13/2015 (10:15-12:15) Sala conferenze MDPs 03/18/2015 (10:15-12:15) Sala conferenze Solving MDPs 03/20/2015 (10:15-12:15) Aula Alpha
More informationOnline Learning, Mistake Bounds, Perceptron Algorithm
Online Learning, Mistake Bounds, Perceptron Algorithm 1 Online Learning So far the focus of the course has been on batch learning, where algorithms are presented with a sample of training data, from which
More informationAdaptive State Feedback Nash Strategies for Linear Quadratic Discrete-Time Games
Adaptive State Feedbac Nash Strategies for Linear Quadratic Discrete-Time Games Dan Shen and Jose B. Cruz, Jr. Intelligent Automation Inc., Rocville, MD 2858 USA (email: dshen@i-a-i.com). The Ohio State
More informationMachine Learning Lecture Notes
Machine Learning Lecture Notes Predrag Radivojac January 25, 205 Basic Principles of Parameter Estimation In probabilistic modeling, we are typically presented with a set of observations and the objective
More informationSequences and infinite series
Sequences and infinite series D. DeTurck University of Pennsylvania March 29, 208 D. DeTurck Math 04 002 208A: Sequence and series / 54 Sequences The lists of numbers you generate using a numerical method
More informationStochastic Compositional Gradient Descent: Algorithms for Minimizing Nonlinear Functions of Expected Values
Stochastic Compositional Gradient Descent: Algorithms for Minimizing Nonlinear Functions of Expected Values Mengdi Wang Ethan X. Fang Han Liu Abstract Classical stochastic gradient methods are well suited
More informationLecture 4: Probabilistic Learning. Estimation Theory. Classification with Probability Distributions
DD2431 Autumn, 2014 1 2 3 Classification with Probability Distributions Estimation Theory Classification in the last lecture we assumed we new: P(y) Prior P(x y) Lielihood x2 x features y {ω 1,..., ω K
More informationLecture 6 Random walks - advanced methods
Lecture 6: Random wals - advanced methods 1 of 11 Course: M362K Intro to Stochastic Processes Term: Fall 2014 Instructor: Gordan Zitovic Lecture 6 Random wals - advanced methods STOPPING TIMES Our last
More informationDiscrete Mathematics and Probability Theory Spring 2014 Anant Sahai Note 10
EECS 70 Discrete Mathematics and Probability Theory Spring 2014 Anant Sahai Note 10 Introduction to Basic Discrete Probability In the last note we considered the probabilistic experiment where we flipped
More informationCOMP 551 Applied Machine Learning Lecture 20: Gaussian processes
COMP 55 Applied Machine Learning Lecture 2: Gaussian processes Instructor: Ryan Lowe (ryan.lowe@cs.mcgill.ca) Slides mostly by: (herke.vanhoof@mcgill.ca) Class web page: www.cs.mcgill.ca/~hvanho2/comp55
More informationPolicy Gradient Reinforcement Learning for Robotics
Policy Gradient Reinforcement Learning for Robotics Michael C. Koval mkoval@cs.rutgers.edu Michael L. Littman mlittman@cs.rutgers.edu May 9, 211 1 Introduction Learning in an environment with a continuous
More informationLecture th January 2009 Fall 2008 Scribes: D. Widder, E. Widder Today s lecture topics
0368.4162: Introduction to Cryptography Ran Canetti Lecture 11 12th January 2009 Fall 2008 Scribes: D. Widder, E. Widder Today s lecture topics Introduction to cryptographic protocols Commitments 1 Cryptographic
More informationProcedia Computer Science 00 (2011) 000 6
Procedia Computer Science (211) 6 Procedia Computer Science Complex Adaptive Systems, Volume 1 Cihan H. Dagli, Editor in Chief Conference Organized by Missouri University of Science and Technology 211-
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 informationNOTES ON EXISTENCE AND UNIQUENESS THEOREMS FOR ODES
NOTES ON EXISTENCE AND UNIQUENESS THEOREMS FOR ODES JONATHAN LUK These notes discuss theorems on the existence, uniqueness and extension of solutions for ODEs. None of these results are original. The proofs
More informationDepartment of Mathematics
Department of Mathematics Ma 3/103 KC Border Introduction to Probability and Statistics Winter 2017 Lecture 8: Expectation in Action Relevant textboo passages: Pitman [6]: Chapters 3 and 5; Section 6.4
More information6 Basic Convergence Results for RL Algorithms
Learning in Complex Systems Spring 2011 Lecture Notes Nahum Shimkin 6 Basic Convergence Results for RL Algorithms We establish here some asymptotic convergence results for the basic RL algorithms, by showing
More informationLecture 16: Perceptron and Exponential Weights Algorithm
EECS 598-005: Theoretical Foundations of Machine Learning Fall 2015 Lecture 16: Perceptron and Exponential Weights Algorithm Lecturer: Jacob Abernethy Scribes: Yue Wang, Editors: Weiqing Yu and Andrew
More informationValue Function Methods. CS : Deep Reinforcement Learning Sergey Levine
Value Function Methods CS 294-112: Deep Reinforcement Learning Sergey Levine Class Notes 1. Homework 2 is due in one week 2. Remember to start forming final project groups and writing your proposal! Proposal
More informationReinforcement Learning. Spring 2018 Defining MDPs, Planning
Reinforcement Learning Spring 2018 Defining MDPs, Planning understandability 0 Slide 10 time You are here Markov Process Where you will go depends only on where you are Markov Process: Information state
More informationSTA414/2104 Statistical Methods for Machine Learning II
STA414/2104 Statistical Methods for Machine Learning II Murat A. Erdogdu & David Duvenaud Department of Computer Science Department of Statistical Sciences Lecture 3 Slide credits: Russ Salakhutdinov Announcements
More informationmin f(x). (2.1) Objectives consisting of a smooth convex term plus a nonconvex regularization term;
Chapter 2 Gradient Methods The gradient method forms the foundation of all of the schemes studied in this book. We will provide several complementary perspectives on this algorithm that highlight the many
More information