- Epsilon-greedy
- Gradient bandit
- Markov decision processes; Bellman equation; Iterative policy evaluation
- Monte carlo control; Epsilon-soft
- Optimistic initial values; Policy iteration
- Importance sampling; Off-policy MC prediction; One-step temporal difference prediction
lucyktan/reinforcement-learning
Folders and files
| Name | Name | Last commit date | ||
|---|---|---|---|---|