Pinned Loading

1. THUDM/slime THUDM/slime Public

   slime is an LLM post-training framework for RL Scaling.

   Python 8.4k 1.2k

2. FixMatch-pytorch FixMatch-pytorch Public

   Unofficial PyTorch implementation of "FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence"

   Python 798 185

3. MPL-pytorch MPL-pytorch Public

   Unofficial PyTorch implementation of "Meta Pseudo Labels"

   Python 389 64

4. rl_pytorch rl_pytorch Public

   Deep Reinforcement Learning Algorithms Implementation in PyTorch

   Jupyter Notebook 27 4

5. reinforcement-learning-kr/alpha_omok reinforcement-learning-kr/alpha_omok Public

   Minimal version of DeepMind AlphaZero

   Python 84 22

6. reinforcement-learning-kr/distributional_rl reinforcement-learning-kr/distributional_rl Public

   Repository for studying distributional rl

   Python 30 8