Popular repositories Loading

1. SDPO SDPO Public

   Reinforcement Learning via Self-Distillation (SDPO)

   Python 711 75

2. SafetyPolytope SafetyPolytope Public

   Learning Safety Constraints for Large Language Models (ICML2025)

   Python 34 6

3. gosafeopt gosafeopt Public

   Globally Safe Model-free Exploration of Dynamical Systems

   Python 32 6

4. safe-learning safe-learning Public

   A collection of algorithms and experiment tools for safe sim to real transfer in robotics.

   Python 23 7

5. opax opax Public

   Python 19 4

6. rewarduq rewarduq Public

   Code for "RewardUQ: A Unified Framework for Uncertainty-Aware Reward Models"

   Python 15 1