Next:
Agents
Up:
415.706FC Datamining and Machine
Previous:
Summary
Reinforcement Learning
Agents
General Problem
Reinforcement Learning Problems
Learning Task
Optimal Policy
Grid-world
Finding Optimal Policies
Q Learning
Q Learning Properties
Q learning Algorithm
Illustrative Example
Convergence
Experimentation Strategies
Updating Sequence
Nondeterministic Rewards and Actions
Temporal Difference Learning
Generalizing from Examples
Relationship to Dynamic Programming
Summary
Patricia Jean Riddle
Wed Jun 23 13:06:34 NZST 1999