Module 2: Ray RLlib
In this module we apply the Ray RLlib software package to solve RL problems.
0
Module 2 Learning Outcomes
1
Intro to RLlib
2
RLlib algorithm methods
3
Slippery Frozen Lake
4
Rendering the trained agent
5
RLlib continued
6
RLlib config syntax
7
Saving/restoring models
8
Cartpole environment
9
Cartpole environment continued
10
RLlib for multi-agent RL
11
Multi-agent RL use cases
12
What do the agents share?
13
Visualizing the trained arena agent
« Previous Chapter
Next Chapter »