Pinned Loading

1. ema-pg ema-pg Public

   Code for "EMA Policy Gradient: Taming Reinforcement Learning for LLMs with EMA Anchor and Top-k KL" (arxiv.org/abs/2602.04417)

   Python 9 2

2. E-SPL E-SPL Public

   Code for "Evolutionary System Prompt Learning for Reinforcement Learning in LLMs" (arxiv.org/abs/2602.14697)

   Python 9

3. world-model-as-a-graph world-model-as-a-graph Public

   Code for "World Model as a Graph: Learning Latent Landmarks for Planning" (ICML 2021 Long Presentation)

   Python 70 4

4. d2ac-actor-critic/d2ac-public d2ac-actor-critic/d2ac-public Public

   Official code for D2AC: Diffusion Actor Meets Distributional Critic (TMLR 2025)

   Python 2

5. genrm-star/genrm-critiques genrm-star/genrm-critiques Public

   GenRM-CoT: Data release for verification rationales

   68 6