Pinned Loading

1. batch-bandits batch-bandits Public

   Implementation of popular bandit algorithms in batch environments.

   Jupyter Notebook 7

2. cmdp cmdp Public

   [ICML 2024] Code for the paper "Efficient Exploration in Average-Reward Constrained RL: Achieving Near-Optimal Regret With Posterior Sampling"

   Python

3. rethinking_lupi rethinking_lupi Public

   Experiments on knowledge transfer techniques in the LUPI paradigm

   Jupyter Notebook 1

4. algorithms algorithms Public

   Algorithms and Data Structures course materials

   Python