Pinned Loading

1. An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & TIS & vLLM & Ray & Async RL)

   Python 9.1k 889

2. A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 🍓 and reasoning techniques.

   6.9k 369

3. Fine-tuned MARL algorithms on SMAC (100% win rates on most scenarios)

   Python 711 134

4. A Multi-threaded Implementation of AlphaZero (C++)

   Python 387 49

5. Multi-agent PPO with noise (97% win rates on Hard scenarios of SMAC)

   Python 76 6

6. Convolutional Neural Network with CUDA (MNIST 99.23%)

   C++ 196 40