Reinforcement Learning (16)
Michael L. Littman
March 23rd, 1999
REINFORCEMENT LEARNING
Types of Learning
Source of Training Signals
Reinforcement-Learning Examples
Reward-to-go Prediction
Solution to Example
Learning Methods
Temporal Difference Methods
CONTROL
RL for Prediction
RL for Control
Certainty Equivalence
TD for Control
Action Values
Learning Policies
Update Rule: Q-learning
Demo...
Next:
REINFORCEMENT LEARNING
