Pinned Loading

1. JAX-CORL JAX-CORL Public

   Clean single-file implementation of offline RL algorithms in JAX

   Python 177 4

2. mahjax mahjax Public

   A GPU-Accelerated Mahjong Simulator for RL in JAX

   Python 24 3

3. remax-rl remax-rl Public

   [ICML2026] Official JAX code for Emergence of Exploration in Policy Gradient Reinforcement Learning via Retrying

   Python 5

4. sotetsuk/pgx sotetsuk/pgx Public

   ♟️ Vectorized RL game environments in JAX

   Python 605 45

5. SymPO SymPO Public

   [TMLR2026] Official code for "On Symmetric Losses for Robust Policy Optimization with Noisy Preferences"

   Python 7

6. PUORL PUORL Public

   [RLC2025] Official code for "Offline Reinforcement Learning with Domain-Unlabeled Data"

   Python 5