Pinned Loading

1. FCSRL FCSRL Public

   Feasibility Consistent Representation Learning for Safe Reinforcement Learning (ICML 2024). Current SOTA model-free safe RL algorithm on safety-gymnasium

   Python 12 2

2. cde-offline-rl cde-offline-rl Public

   Learning from Sparse Offline Datasets via Conservative Density Estimation (ICLR 2024)

   Python 3

3. Bridge-LLM-reasoning Bridge-LLM-reasoning Public

   Behavior Injection: Preparing Language Models for Reinforcement Learning (NeurIPS 2025)

   Python 14

4. SalesforceAIResearch/PretrainRL-pipeline SalesforceAIResearch/PretrainRL-pipeline Public

   An automated data pipeline scaling RL to pretraining levels

   Python 72 6