Pinned Loading

1. TD3BCpp TD3BCpp Public

   Robust Offline Reinforcement Learning from Contaminated Demonstrations

   Python

2. NES-HT NES-HT Public

   Hard-Thresholding Meets Evolution Strategies in Reinforcement Learning

   Python 4

3. SelectiveDPO SelectiveDPO Public

   Principled Data Selection for Alignment: The Hidden Risks of Difficult Examples

   Python 48 1

4. PALU PALU Public

   Concise Reasoning in the Lens of Lagrangian Optimization

   1