5
Trust Region Policy Optimization
Reinforcement Learning
Preface
1
Multi-armed Bandits
2
Markov Decision Processes
3
Dynamic Programming
4
Policy Gradient Methods
5
Trust Region Policy Optimization
Interactive Learning
6
A Two-armed Bandit Warm-up
7
A Two-armed Bandit Game
References
Table of contents
5.1
KL Divergence
5
Trust Region Policy Optimization
5.1
KL Divergence
4
Policy Gradient Methods
6
A Two-armed Bandit Warm-up