Overview Example (TD-Gammon) Admission Why approximate RL is hard TD() Fitted value iteration (collocation) Example (k-nn for hill-car)
|
|
|
- Abraham Reeves
- 6 years ago
- Views:
Transcription
1 Function Approximation in Reinforcement Learning Gordon Geo November 5, 999
2 Overview Example (TD-Gammon) Admission Why approximate RL is hard TD() Fitted value iteration (collocation) Example (k-nn for hill-car)
3 Backgammon Object: move all pieces o rst Opponent can block you or send you backwards
4 Backgammon cont'd 30 pieces (5 each for you and opponent) 24 points + bar + o = 26 locations 2 dice (36 possible rolls) Rough (over)estimate: : states Branching factor: 36 about 20 Complications: gammon, backgammon, doubling cube
5 TD-Gammon [Tesauro] Neural network with hidden layer 200 inputs: board position hidden units output: win probability Sigmoids on all hidden, output units (range [0 ])
6 >< >: win loss 0 Using RL Win probability is value function if: 8 Reinforcement = 0 game not over Discount is = weights for network should approximately satisfy Bellman So equation Warning: devil is in details! For now: ignore details, use TD(0)
7 Write v(xjw) for output of net with inputs x and weights w Given a transition x a r y Update w := w old + (r + v(yjw old ) ; v(xjw old )) r w v(xjw)j wold Review of TD(0) Ignores a (assumes it was chosen greedily)
8 TD(0) is not gradient descent Max isn't dierentiable Haven't said how to choose transition (won't be independent) Step direction is not a full gradient
9 Write Error(x r yjw) =(r + v(yjw) ; v(xjw)) 2 Write Error(x r yjw w 2 )=(r + v(yjw 2 ) ; v(xjw )) 2 TD uses r w Error(x r yjw w old )j wold GD would use r w Error(x r yjw)j wold Bellman error
10 Raw: Are there at least k of my pieces at location x? Representation Raw board or raw + expert features Are there at least k opposing pieces at location x? Is it my turn? My opponent's? For k>k max, extra pieces added to last unit's activation k max is 4 for points, for bar and o All inputs scaled to lie approximately in [0 ]
11 A useful trick position+die roll position position+die roll Die rolls aren't represented Implicit in lookahead choose random
12 Training Start from zero knowledge Self play (up to.5 million games) Data: state, die roll, action, reinforcement, state,... Compress to: state, state,..., state, win/loss
13 Results features give pretty good player (close to best computer Raw at time) player Raw+expert features give world-class player Absolute probabilities not so hot (0% error) Relative probabilities very good
14 What's easy about RL in backgammon Random strong eective discount kick out of local minima Guaranteed to terminate Perfect model, no hidden state Self-play allows huge training set
15 function approximator Nonlinear usual worry of local minima data distribution Changing changing policy causes change in importance of states What's hard about RL in backgammon Game (minimax instead of min or max) complete divergence is also possible [Van Roy] could get stuck (checkers, go) could oscillate forever wrong distribution could cause divergence [Gordon, Baird]
16 Huge variety of approximate RL algorithms Incremental vs. batch Model-based vs. direct Kind of function approximation Control vs. estimation State-values vs. action-values (V vs. Q) Vs. no values (policy only)
17 One fundamental question What does \approximate solution to Bellman equations" mean? Subquestion: how do we nd one?
18 Possible answers Bellman equations are a red herring Minimum squared Bellman error Minimum weighted squared Bellman error Relaxation of Bellman equations satisfy at some states other
19 Fit a line to each row: v(i j)=a j + b j i Minimum SBE example 3 00 grid of states
20 Minimum SBE example cont'd Exact Min SBE Min weighted SBE
21 action a Fixed policy Measures how important (x a) is to value of Flows F (x a) = expected # of times we visit state x and perform Fixed starting frequencies f 0 (x)
22 Visit (s a) at steps 2 and 7, discounted ow is Flows cont'd If <, use discounted ows For all, F satises conservation equation 0 X A F (x a) f0 (x)+ X y a F (y a)p (xjy a) a
23 F = F Aside: Can nd optimal ows using nonnegativity, conservation, and of reinforcement maximization This is dual (in sense of LP) to solving Bellman equations Optimal ows are optimal ows Optimal ows determine optimal policy maximizes total expected discounted reinforcement F X E(r(x a))f (x a) x a
24 Choosing weights Optimal ows would be good weights If just one policy, can nd ows Otherwise, chicken and egg problem Iterative improvement? Yes, but none known to converge. Research question: EM algorithm?
25 ij is probability of going to state j from state i, r i is expected p reinforcement state is i Matrix form of TD(0) Assume one policy, n states Write P for transition probability matrix (n n) Write r for reinforcement vector (n ) P i (ith row of P ) is distribution of next state given that current
26 Write E = P ; I Matrix form of TD(0) cont'd Write v for value function (n ) v i is value of state i (Pv + r) ; v is vector of Bellman errors Bellman equation is (P ; I)v + r =0
27 Assume w = 0 corresponds to v(x) = 0 for all x Matrix form of TD(0) cont'd Assume v is linear in parameters w (k ) r w v i is a constant k-vector (call it A i ) r w v is a constant n k matrix (call it A)
28 = X x = X x = X x = X x P (x)a x (r x + w X y Expected update E((r + v(yjw) ; v(xjw))r w v(xjw)) P (x)e((r + v(yjw) ; v(xjw))a x jx) P (x)a x (E(rjx)+E(v(yjw x)) ; v(xjw)) P (x)a x (r x + E(A y wjx) ; A x w) P (yjx)a y ; A x w)
29 P (x)a x (r x + w X y = X x = X x = X x Expected update cont'd X P (yjx)a y ; A x w) x P (x)a x (r x + w (P T x A) ; A x w) P (x)a x (r x +(P T x A ; A x) w) P (x)a x (r x +(P x ; U x ) T A w) = (DA) T (R +(P ; I)Aw)
30 Data x r x 2 r 2 ::: TD(0) uses -step error (r + x 2 ) ; x Could use 2-step error (r + r x 3 ) ; x TD() weights k-step error proportional to k TD() As!, approaches supervised learning
31 So (I ; A T DEA) has radius < for small enough of expectation follows tricky stochastic argument Convergence show that random perturbations don't kill convergence [Dayan, to Convergence Expected update is A T D(EAw + R) Can write w := (I ; A T DEA)w old + k +error Sutton (988) proved that A T DEA is positive denite So 9 a norm in which (I ; A T DEA) is a contraction Jaakola, Jordan, Singh, Tsitsiklis, Van Roy]
32 TD(0) and min weighted SBE TD(0) does not nd minimum of weighted SBE, but close TD(0) solves A T D(EAw + R) =0 Min WSBE satises (DEA) T D(EAw + R) =0 solving TD eqs in batch mode is called LS-TD (for least Note: even though it's not minimizing squared anything) [Bradtke squares, & Barto]
33 If k parameters, might expect m = k Collocation Satisfy Bellman equations exactly at m states But Bellman equations are nonlinear, so in general might need more or fewer than k equations solution might not be unique hard to nd
34 Averagers For some function approximators [Gordon, Van Roy] m = k works solution is unique easy to nd Called averagers linear interpolation on mesh, multilinear interpolation Examples: grid, k-nearest-neighbor on
35 Pick a sample X Remember v(x) only for x 2 X Fitted value iteration nd v(x) for x 62 X use k-nearest-neighbor, linear interpolation, To... One step of tted VI has two parts: Do a step of exact VI Replace result with a cheap approximation
36 Approximate with v(x) = v(y) = w Approximators as mappings v(y) (,5) (3,3) v(x) MDP with 2 states, so value fn is 2D: (v(x) v(y))
37 7! M A 7! M A Approximators as mappings
38 7! M A 7! M A Exaggeration Two similar target value functions Larger dierence between tted functions Exaggeration = max-norm expansion
39 Goal Hill-car Forward Reverse Gravity tries to drive up hill, but engine is weak so must back up to Car momentum get
40 Results Approximate Exact
41 Results the hard way
42 renement (use ows, policy uncertainty, and value Adaptive to decide where to split) [Munos & Moore] uncertainty Interesting topics left uncovered Hidden state (similar problems to fn approx) Eligibility traces Policy iteration and -PI Actor-critic architectures Duality and RL Stopping problems
43 6 +7 Bonus extra slide: RL counterexample with values (0 0 0) Start one backup: (0 ) Do a line: (; ) Fit another backup: (0 + 7 Do 6 ) For 6 7, divergence
CS 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.
Lecture 23: Reinforcement Learning
Lecture 23: Reinforcement Learning MDPs revisited Model-based learning Monte Carlo value function estimation Temporal-difference (TD) learning Exploration November 23, 2006 1 COMP-424 Lecture 23 Recall:
Reinforcement Learning
Reinforcement Learning Temporal Difference Learning Temporal difference learning, TD prediction, Q-learning, elibigility traces. (many slides from Marc Toussaint) Vien Ngo Marc Toussaint University of
CS599 Lecture 1 Introduction To RL
CS599 Lecture 1 Introduction To RL Reinforcement Learning Introduction Learning from rewards Policies Value Functions Rewards Models of the Environment Exploitation vs. Exploration Dynamic Programming
Chapter 8: Generalization and Function Approximation
Chapter 8: Generalization and Function Approximation Objectives of this chapter: Look at how experience with a limited part of the state set be used to produce good behavior over a much larger part. Overview
Reinforcement Learning. Yishay Mansour Tel-Aviv University
Reinforcement Learning Yishay Mansour Tel-Aviv University 1 Reinforcement Learning: Course Information Classes: Wednesday Lecture 10-13 Yishay Mansour Recitations:14-15/15-16 Eliya Nachmani Adam Polyak
Lecture 1: March 7, 2018
Reinforcement Learning Spring Semester, 2017/8 Lecture 1: March 7, 2018 Lecturer: Yishay Mansour Scribe: ym DISCLAIMER: Based on Learning and Planning in Dynamical Systems by Shie Mannor c, all rights
CSE 190: Reinforcement Learning: An Introduction. Chapter 8: Generalization and Function Approximation. Pop Quiz: What Function Are We Approximating?
CSE 190: Reinforcement Learning: An Introduction Chapter 8: Generalization and Function Approximation Objectives of this chapter: Look at how experience with a limited part of the state set be used to
CS 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
Reinforcement Learning for Continuous. Action using Stochastic Gradient Ascent. Hajime KIMURA, Shigenobu KOBAYASHI JAPAN
Reinforcement Learning for Continuous Action using Stochastic Gradient Ascent Hajime KIMURA, Shigenobu KOBAYASHI Tokyo Institute of Technology, 4259 Nagatsuda, Midori-ku Yokohama 226-852 JAPAN Abstract:
CSE 190: Reinforcement Learning: An Introduction. Chapter 8: Generalization and Function Approximation. Pop Quiz: What Function Are We Approximating?
CSE 190: Reinforcement Learning: An Introduction Chapter 8: Generalization and Function Approximation Objectives of this chapter: Look at how experience with a limited part of the state set be used to
Georey J. Gordon. Carnegie Mellon University. Pittsburgh PA Bellman-Ford single-destination shortest paths algorithm
Stable Function Approximation in Dynamic Programming Georey J. Gordon Computer Science Department Carnegie Mellon University Pittsburgh PA 53 ggordon@cs.cmu.edu Abstract The success of reinforcement learning
CS599 Lecture 2 Function Approximation in RL
CS599 Lecture 2 Function Approximation in RL Look at how experience with a limited part of the state set be used to produce good behavior over a much larger part. Overview of function approximation (FA)
Fast Gradient-Descent Methods for Temporal-Difference Learning with Linear Function Approximation
Fast Gradient-Descent Methods for Temporal-Difference Learning with Linear Function Approximation Rich Sutton, University of Alberta Hamid Maei, University of Alberta Doina Precup, McGill University Shalabh
Reinforcement Learning
Reinforcement Learning Function approximation Daniel Hennes 19.06.2017 University Stuttgart - IPVS - Machine Learning & Robotics 1 Today Eligibility traces n-step TD returns Forward and backward view Function
Reinforcement 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
Reinforcement 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
Machine Learning. Machine Learning: Jordan Boyd-Graber University of Maryland REINFORCEMENT LEARNING. Slides adapted from Tom Mitchell and Peter Abeel
Machine Learning Machine Learning: Jordan Boyd-Graber University of Maryland REINFORCEMENT LEARNING Slides adapted from Tom Mitchell and Peter Abeel Machine Learning: Jordan Boyd-Graber UMD Machine Learning
Christopher Watkins and Peter Dayan. Noga Zaslavsky. The Hebrew University of Jerusalem Advanced Seminar in Deep Learning (67679) November 1, 2015
Q-Learning Christopher Watkins and Peter Dayan Noga Zaslavsky The Hebrew University of Jerusalem Advanced Seminar in Deep Learning (67679) November 1, 2015 Noga Zaslavsky Q-Learning (Watkins & Dayan, 1992)
Reinforcement Learning
Reinforcement Learning Function approximation Mario Martin CS-UPC May 18, 2018 Mario Martin (CS-UPC) Reinforcement Learning May 18, 2018 / 65 Recap Algorithms: MonteCarlo methods for Policy Evaluation
Grundlagen der Künstlichen Intelligenz
Grundlagen der Künstlichen Intelligenz Reinforcement learning II Daniel Hennes 11.12.2017 (WS 2017/18) University Stuttgart - IPVS - Machine Learning & Robotics 1 Today Eligibility traces n-step TD returns
Machine Learning I Reinforcement Learning
Machine Learning I Reinforcement Learning Thomas Rückstieß Technische Universität München December 17/18, 2009 Literature Book: Reinforcement Learning: An Introduction Sutton & Barto (free online version:
Lecture 7: Value Function Approximation
Lecture 7: Value Function Approximation Joseph Modayil Outline 1 Introduction 2 3 Batch Methods Introduction Large-Scale Reinforcement Learning Reinforcement learning can be used to solve large problems,
MDP 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
Introduction to Reinforcement Learning. CMPT 882 Mar. 18
Introduction to Reinforcement Learning CMPT 882 Mar. 18 Outline for the week Basic ideas in RL Value functions and value iteration Policy evaluation and policy improvement Model-free RL Monte-Carlo and
Generalization and Function Approximation
Generalization and Function Approximation 0 Generalization and Function Approximation Suggested reading: Chapter 8 in R. S. Sutton, A. G. Barto: Reinforcement Learning: An Introduction MIT Press, 1998.
Reinforcement Learning
Reinforcement Learning 1 Reinforcement Learning Mainly based on Reinforcement Learning An Introduction by Richard Sutton and Andrew Barto Slides are mainly based on the course material provided by the
Lecture 25: Learning 4. Victor R. Lesser. CMPSCI 683 Fall 2010
Lecture 25: Learning 4 Victor R. Lesser CMPSCI 683 Fall 2010 Final Exam Information Final EXAM on Th 12/16 at 4:00pm in Lederle Grad Res Ctr Rm A301 2 Hours but obviously you can leave early! Open Book
Proceedings of the International Conference on Neural Networks, Orlando Florida, June Leemon C. Baird III
Proceedings of the International Conference on Neural Networks, Orlando Florida, June 1994. REINFORCEMENT LEARNING IN CONTINUOUS TIME: ADVANTAGE UPDATING Leemon C. Baird III bairdlc@wl.wpafb.af.mil Wright
Deep Reinforcement Learning
Martin Matyášek Artificial Intelligence Center Czech Technical University in Prague October 27, 2016 Martin Matyášek VPD, 2016 1 / 50 Reinforcement Learning in a picture R. S. Sutton and A. G. Barto 2015
Today s s Lecture. Applicability of Neural Networks. Back-propagation. Review of Neural Networks. Lecture 20: Learning -4. Markov-Decision Processes
Today s s Lecture Lecture 20: Learning -4 Review of Neural Networks Markov-Decision Processes Victor Lesser CMPSCI 683 Fall 2004 Reinforcement learning 2 Back-propagation Applicability of Neural Networks
Lecture 15: Bandit problems. Markov Processes. Recall: Lotteries and utilities
Lecture 15: Bandit problems. Markov Processes Bandit problems Action values (and now to compute them) Exploration-exploitation trade-off Simple exploration strategies -greedy Softmax (Boltzmann) exploration
Reinforcement Learning
Reinforcement Learning Ron Parr CompSci 7 Department of Computer Science Duke University With thanks to Kris Hauser for some content RL Highlights Everybody likes to learn from experience Use ML techniques
Lecture 5: Logistic Regression. Neural Networks
Lecture 5: Logistic Regression. Neural Networks Logistic regression Comparison with generative models Feed-forward neural networks Backpropagation Tricks for training neural networks COMP-652, Lecture
(Deep) Reinforcement Learning
Martin Matyášek Artificial Intelligence Center Czech Technical University in Prague October 27, 2016 Martin Matyášek VPD, 2016 1 / 17 Reinforcement Learning in a picture R. S. Sutton and A. G. Barto 2015
Open Theoretical Questions in Reinforcement Learning
Open Theoretical Questions in Reinforcement Learning Richard S. Sutton AT&T Labs, Florham Park, NJ 07932, USA, sutton@research.att.com, www.cs.umass.edu/~rich Reinforcement learning (RL) concerns the problem
Review: TD-Learning. TD (SARSA) Learning for Q-values. Bellman Equations for Q-values. P (s, a, s )[R(s, a, s )+ Q (s, (s ))]
![Review: TD-Learning. TD (SARSA) Learning for Q-values. Bellman Equations for Q-values. P (s, a, s )[R(s, a, s )+ Q (s, (s ))]](/thumbs/94/119187228.jpg "Review: TD-Learning. TD (SARSA) Learning for Q-values. Bellman Equations for Q-values. P (s, a, s )[R(s, a, s )+ Q (s, (s ))]")
Review: TD-Learning function TD-Learning(mdp) returns a policy Class #: Reinforcement Learning, II 8s S, U(s) =0 set start-state s s 0 choose action a, using -greedy policy based on U(s) U(s) U(s)+ [r
CMU Lecture 12: Reinforcement Learning. Teacher: Gianni A. Di Caro
CMU 15-781 Lecture 12: Reinforcement Learning Teacher: Gianni A. Di Caro REINFORCEMENT LEARNING Transition Model? State Action Reward model? Agent Goal: Maximize expected sum of future rewards 2 MDP PLANNING
Reinforcement Learning with Function Approximation. Joseph Christian G. Noel
Reinforcement Learning with Function Approximation Joseph Christian G. Noel November 2011 Abstract Reinforcement learning (RL) is a key problem in the field of Artificial Intelligence. The main goal is
Deep Reinforcement Learning SISL. Jeremy Morton (jmorton2) November 7, Stanford Intelligent Systems Laboratory
Deep Reinforcement Learning Jeremy Morton (jmorton2) November 7, 2016 SISL Stanford Intelligent Systems Laboratory Overview 2 1 Motivation 2 Neural Networks 3 Deep Reinforcement Learning 4 Deep Learning
Basics of reinforcement learning
Basics of reinforcement learning Lucian Buşoniu TMLSS, 20 July 2018 Main idea of reinforcement learning (RL) Learn a sequential decision policy to optimize the cumulative performance of an unknown system
Neural networks. Chapter 20. Chapter 20 1
Neural networks Chapter 20 Chapter 20 1 Outline Brains Neural networks Perceptrons Multilayer networks Applications of neural networks Chapter 20 2 Brains 10 11 neurons of > 20 types, 10 14 synapses, 1ms
Planning 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
CSC321 Lecture 8: Optimization
CSC321 Lecture 8: Optimization Roger Grosse Roger Grosse CSC321 Lecture 8: Optimization 1 / 26 Overview We ve talked a lot about how to compute gradients. What do we actually do with them? Today s lecture:
Introduction to Reinforcement Learning
Introduction to Reinforcement Learning Rémi Munos SequeL project: Sequential Learning http://researchers.lille.inria.fr/ munos/ INRIA Lille - Nord Europe Machine Learning Summer School, September 2011,
Reinforcement learning an introduction
Reinforcement learning an introduction Prof. Dr. Ann Nowé Computational Modeling Group AIlab ai.vub.ac.be November 2013 Reinforcement Learning What is it? Learning from interaction Learning about, from,
Course basics. CSE 190: Reinforcement Learning: An Introduction. Last Time. Course goals. The website for the class is linked off my homepage.
Course basics CSE 190: Reinforcement Learning: An Introduction The website for the class is linked off my homepage. Grades will be based on programming assignments, homeworks, and class participation.
Lecture 8: Policy Gradient
Lecture 8: Policy Gradient Hado van Hasselt Outline 1 Introduction 2 Finite Difference Policy Gradient 3 Monte-Carlo Policy Gradient 4 Actor-Critic Policy Gradient Introduction Vapnik s rule Never solve
Lecture 4: Approximate dynamic programming
IEOR 800: Reinforcement learning By Shipra Agrawal Lecture 4: Approximate dynamic programming Deep Q Networks discussed in the last lecture are an instance of approximate dynamic programming. These are
REINFORCE Framework for Stochastic Policy Optimization and its use in Deep Learning
REINFORCE Framework for Stochastic Policy Optimization and its use in Deep Learning Ronen Tamari The Hebrew University of Jerusalem Advanced Seminar in Deep Learning (#67679) February 28, 2016 Ronen Tamari
Reinforcement Learning. Spring 2018 Defining MDPs, Planning
Reinforcement Learning Spring 2018 Defining MDPs, Planning understandability 0 Slide 10 time You are here Markov Process Where you will go depends only on where you are Markov Process: Information state
Introduction to Reinforcement Learning. Part 6: Core Theory II: Bellman Equations and Dynamic Programming
Introduction to Reinforcement Learning Part 6: Core Theory II: Bellman Equations and Dynamic Programming Bellman Equations Recursive relationships among values that can be used to compute values The tree
y(x n, w) t n 2. (1)
Network training: Training a neural network involves determining the weight parameter vector w that minimizes a cost function. Given a training set comprising a set of input vector {x n }, n = 1,...N,
INF 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)
Decision making, Markov decision processes
Decision making, Markov decision processes Solved tasks Collected by: Jiří Kléma, klema@fel.cvut.cz Spring 2017 The main goal: The text presents solved tasks to support labs in the A4B33ZUI course. 1 Simple
Be able to define the following terms and answer basic questions about them:
CS440/ECE448 Section Q Fall 2017 Final Review Be able to define the following terms and answer basic questions about them: Probability o Random variables, axioms of probability o Joint, marginal, conditional
Prof. Dr. Ann Nowé. Artificial Intelligence Lab ai.vub.ac.be
REINFORCEMENT LEARNING AN INTRODUCTION Prof. Dr. Ann Nowé Artificial Intelligence Lab ai.vub.ac.be REINFORCEMENT LEARNING WHAT IS IT? What is it? Learning from interaction Learning about, from, and while
Q-Learning in Continuous State Action Spaces
Q-Learning in Continuous State Action Spaces Alex Irpan alexirpan@berkeley.edu December 5, 2015 Contents 1 Introduction 1 2 Background 1 3 Q-Learning 2 4 Q-Learning In Continuous Spaces 4 5 Experimental
CS 188 Introduction to Fall 2007 Artificial Intelligence Midterm
NAME: SID#: Login: Sec: 1 CS 188 Introduction to Fall 2007 Artificial Intelligence Midterm You have 80 minutes. The exam is closed book, closed notes except a one-page crib sheet, basic calculators only.
ECE521 Lectures 9 Fully Connected Neural Networks
ECE521 Lectures 9 Fully Connected Neural Networks Outline Multi-class classification Learning multi-layer neural networks 2 Measuring distance in probability space We learnt that the squared L2 distance
CSC321 Lecture 7: Optimization
CSC321 Lecture 7: Optimization Roger Grosse Roger Grosse CSC321 Lecture 7: Optimization 1 / 25 Overview We ve talked a lot about how to compute gradients. What do we actually do with them? Today s lecture:
Chapter 3: The Reinforcement Learning Problem
Chapter 3: The Reinforcement Learning Problem Objectives of this chapter: describe the RL problem we will be studying for the remainder of the course present idealized form of the RL problem for which
Do not tear exam apart!
6.036: Final Exam: Fall 2017 Do not tear exam apart! This is a closed book exam. Calculators not permitted. Useful formulas on page 1. The problems are not necessarily in any order of di culty. Record
Introduction to Reinforcement Learning
CSCI-699: Advanced Topics in Deep Learning 01/16/2019 Nitin Kamra Spring 2019 Introduction to Reinforcement Learning 1 What is Reinforcement Learning? So far we have seen unsupervised and supervised learning.
4. Multilayer Perceptrons
4. Multilayer Perceptrons This is a supervised error-correction learning algorithm. 1 4.1 Introduction A multilayer feedforward network consists of an input layer, one or more hidden layers, and an output
Multi-Player Residual Advantage Learning With General Function Approximation
Multi-Player Residual Advantage Learning With General Function Approximation Mance E. Harmon Wright Laboratory WL/AACF 2241 Avionics Circle Wright-Patterson Air Force Base, OH 45433-7308 harmonme@aa.wpafb.mil
Artificial Neural Networks" and Nonparametric Methods" CMPSCI 383 Nov 17, 2011!
Artificial Neural Networks" and Nonparametric Methods" CMPSCI 383 Nov 17, 2011! 1 Todayʼs lecture" How the brain works (!)! Artificial neural networks! Perceptrons! Multilayer feed-forward networks! Error
In Advances in Neural Information Processing Systems 6. J. D. Cowan, G. Tesauro and. Convergence of Indirect Adaptive. Andrew G.
In Advances in Neural Information Processing Systems 6. J. D. Cowan, G. Tesauro and J. Alspector, (Eds.). Morgan Kaufmann Publishers, San Fancisco, CA. 1994. Convergence of Indirect Adaptive Asynchronous
Internet 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
Reinforcement Learning. Up until now we have been
Reinforcement Learning Slides by Rich Sutton Mods by Dan Lizotte Refer to Reinforcement Learning: An Introduction by Sutton and Barto Alpaydin Chapter 16 Up until now we have been Supervised Learning Classifying,
Reinforcement Learning
Reinforcement Learning RL in continuous MDPs March April, 2015 Large/Continuous MDPs Large/Continuous state space Tabular representation cannot be used Large/Continuous action space Maximization over action
Learning Tetris. 1 Tetris. February 3, 2009
Learning Tetris Matt Zucker Andrew Maas February 3, 2009 1 Tetris The Tetris game has been used as a benchmark for Machine Learning tasks because its large state space (over 2 200 cell configurations are
Markov Decision Processes and Solving Finite Problems. February 8, 2017
Markov Decision Processes and Solving Finite Problems February 8, 2017 Overview of Upcoming Lectures Feb 8: Markov decision processes, value iteration, policy iteration Feb 13: Policy gradients Feb 15:
Reinforcement Learning
Reinforcement Learning March May, 2013 Schedule Update Introduction 03/13/2015 (10:15-12:15) Sala conferenze MDPs 03/18/2015 (10:15-12:15) Sala conferenze Solving MDPs 03/20/2015 (10:15-12:15) Aula Alpha
The Simplex and Policy Iteration Methods are Strongly Polynomial for the Markov Decision Problem with Fixed Discount
The Simplex and Policy Iteration Methods are Strongly Polynomial for the Markov Decision Problem with Fixed Discount Yinyu Ye Department of Management Science and Engineering and Institute of Computational
Average Reward Parameters
Simulation-Based Optimization of Markov Reward Processes: Implementation Issues Peter Marbach 2 John N. Tsitsiklis 3 Abstract We consider discrete time, nite state space Markov reward processes which depend
Administration. CSCI567 Machine Learning (Fall 2018) Outline. Outline. HW5 is available, due on 11/18. Practice final will also be available soon.
Administration CSCI567 Machine Learning Fall 2018 Prof. Haipeng Luo U of Southern California Nov 7, 2018 HW5 is available, due on 11/18. Practice final will also be available soon. Remaining weeks: 11/14,
6.231 DYNAMIC PROGRAMMING LECTURE 6 LECTURE OUTLINE
6.231 DYNAMIC PROGRAMMING LECTURE 6 LECTURE OUTLINE Review of Q-factors and Bellman equations for Q-factors VI and PI for Q-factors Q-learning - Combination of VI and sampling Q-learning and cost function
Reinforcement Learning (1)
Reinforcement Learning 1 Reinforcement Learning (1) Machine Learning 64-360, Part II Norman Hendrich University of Hamburg, Dept. of Informatics Vogt-Kölln-Str. 30, D-22527 Hamburg hendrich@informatik.uni-hamburg.de
Keywords: machine learning, reinforcement learning, dynamic programming, Markov decision processes (MDPs), linear programming, convex programming, fun
Approximate Solutions to Markov Decision Processes Georey J. Gordon June 1999 CMU-CS-99-143 School of Computer Science Carnegie Mellon University Pittsburgh, PA 15213 Submitted in partial fulllment of
Temporal difference learning
Temporal difference learning AI & Agents for IET Lecturer: S Luz http://www.scss.tcd.ie/~luzs/t/cs7032/ February 4, 2014 Recall background & assumptions Environment is a finite MDP (i.e. A and S are finite).
Reinforcement Learning in Continuous Time and Space
LETTER Communicated by Peter Dayan Reinforcement Learning in Continuous Time and Space Kenji Doya ATR Human Information Processing Research Laboratories, Soraku, Kyoto 619-288, Japan This article presents
CSE 417T: Introduction to Machine Learning. Final Review. Henry Chai 12/4/18
CSE 417T: Introduction to Machine Learning Final Review Henry Chai 12/4/18 Overfitting Overfitting is fitting the training data more than is warranted Fitting noise rather than signal 2 Estimating! "#$
Prioritized 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
Introduction to Natural Computation. Lecture 9. Multilayer Perceptrons and Backpropagation. Peter Lewis
Introduction to Natural Computation Lecture 9 Multilayer Perceptrons and Backpropagation Peter Lewis 1 / 25 Overview of the Lecture Why multilayer perceptrons? Some applications of multilayer perceptrons.
Lecture 3: The Reinforcement Learning Problem
Lecture 3: The Reinforcement Learning Problem Objectives of this lecture: describe the RL problem we will be studying for the remainder of the course present idealized form of the RL problem for which
Machine 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
Exponential Moving Average Based Multiagent Reinforcement Learning Algorithms
Artificial Intelligence Review manuscript No. (will be inserted by the editor) Exponential Moving Average Based Multiagent Reinforcement Learning Algorithms Mostafa D. Awheda Howard M. Schwartz Received:
On 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
15-889e Policy Search: Gradient Methods Emma Brunskill. All slides from David Silver (with EB adding minor modificafons), unless otherwise noted
15-889e Policy Search: Gradient Methods Emma Brunskill All slides from David Silver (with EB adding minor modificafons), unless otherwise noted Outline 1 Introduction 2 Finite Difference Policy Gradient
Adaptive linear quadratic control using policy. iteration. Steven J. Bradtke. University of Massachusetts.
Adaptive linear quadratic control using policy iteration Steven J. Bradtke Computer Science Department University of Massachusetts Amherst, MA 01003 bradtke@cs.umass.edu B. Erik Ydstie Department of Chemical
Temporal Difference. Learning KENNETH TRAN. Principal Research Engineer, MSR AI
Temporal Difference Learning KENNETH TRAN Principal Research Engineer, MSR AI Temporal Difference Learning Policy Evaluation Intro to model-free learning Monte Carlo Learning Temporal Difference Learning
Reinforcement Learning
Reinforcement Learning Dipendra Misra Cornell University dkm@cs.cornell.edu https://dipendramisra.wordpress.com/ Task Grasp the green cup. Output: Sequence of controller actions Setup from Lenz et. al.
Neural networks and optimization
Neural networks and optimization Nicolas Le Roux INRIA 8 Nov 2011 Nicolas Le Roux (INRIA) Neural networks and optimization 8 Nov 2011 1 / 80 1 Introduction 2 Linear classifier 3 Convolutional neural networks
Value 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
Data Mining Part 5. Prediction
Data Mining Part 5. Prediction 5.5. Spring 2010 Instructor: Dr. Masoud Yaghini Outline How the Brain Works Artificial Neural Networks Simple Computing Elements Feed-Forward Networks Perceptrons (Single-layer,
MS&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
An Adaptive Clustering Method for Model-free Reinforcement Learning
An Adaptive Clustering Method for Model-free Reinforcement Learning Andreas Matt and Georg Regensburger Institute of Mathematics University of Innsbruck, Austria {andreas.matt, georg.regensburger}@uibk.ac.at
PART A and ONE question from PART B; or ONE question from PART A and TWO questions from PART B.
Advanced Topics in Machine Learning, GI13, 2010/11 Advanced Topics in Machine Learning, GI13, 2010/11 Answer any THREE questions. Each question is worth 20 marks. Use separate answer books Answer any THREE
Balancing and Control of a Freely-Swinging Pendulum Using a Model-Free Reinforcement Learning Algorithm
Balancing and Control of a Freely-Swinging Pendulum Using a Model-Free Reinforcement Learning Algorithm Michail G. Lagoudakis Department of Computer Science Duke University Durham, NC 2778 mgl@cs.duke.edu