In this notebook I will:
- Create bandit algorithm
- Help you understand the effect of epsilon on exploration and learn about the exploration/exploitation tradeoff
step_sizes = [0.01, 0.1, 0.5, 1.0, '1/N(A)']
-
Notifications
You must be signed in to change notification settings - Fork 0
karandeepdps/step_size_epsilon_vs_reward_distributio
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
Ablation study on maximizing the RL reward using hyperparameter tuning.
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published