Machine Learning Summer School 2006 - Canberra

Reinforcement Learning

author: Satinder Singh, Public Policy and Sociology, University of Michigan

Description

MDPs/VI,
Q learning (w/ proof),
TD(lambda),
Function approximation,
options,
PSRs

Categories

Top: Computer Science: Machine Learning: Reinforcement Learning

You might be experiencing some problems with Your Video player.

*Slides*
0:01	Reinforcement Learning: A Tutorial
2:51	Outline
4:00	RL is Learning from Interaction
6:21	RL (another view)
9:29	Key Ideas in RL
10:23	Demos...
10:27	Demos...
11:16	Demos...
12:27	Keepaway Soccer (Stone & Sutton)
13:01	Keepaway Soccer (Stone & Sutton)
13:04	Tetris Demo
14:17	History & Place
14:29	Place
16:57	(Partial) History
17:56	(Partial) History...
18:17	RL and Machine Learning
20:11	(Partial) List of Applications
21:10	List of Conferences and Journals
21:12	Model of Agent-Environment Interaction
23:07	Markov Decision Processes
24:48	MDP Preliminaries
31:12	MDP Preliminaries...
33:12	Bellman Optimality Equations
37:51	Bellman Optimality Equations
42:00	Graphical View of MDPs
43:04	Planning & Learning
43:22	Planning in MDPs
47:01	Planning in MDPs
48:01	Planning in MDPs
49:49	Convergence of Value Iteration
49:56	Proof of the DP contraction
54:13	Learning in MDPs
57:21	Indirect Methods for Learning in MDPs

Lecture rating

People found this lecture:
Worth seeing
because it is:
Valuable and informative
Well presented
Easily understandable
Acceptably recorded
You need to login to cast your vote.

Report a problem or upload files

If you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.