Pinned Loading

1. SakanaAI/AI-Scientist SakanaAI/AI-Scientist Public

   The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑‍🔬

   Jupyter Notebook 12.2k 1.8k

2. purejaxrl purejaxrl Public

   Really Fast End-to-End Jax RL Implementations

   Python 1k 83

3. FLAIROx/JaxMARL FLAIROx/JaxMARL Public

   Multi-Agent Reinforcement Learning with JAX

   Python 752 140

4. popjaxrl popjaxrl Public

   Benchmarking RL for POMDPs in Pure JAX [Code for "Structured State Space Models for In-Context Reinforcement Learning" (NeurIPS 2023)]

   Python 112 10

5. DiscoPOP DiscoPOP Public

   Code for Discovering Preference Optimization Algorithms with and for Large Language Models

   Python 65 34

6. JaxLife JaxLife Public

   An Open-Ended Agentic Simulator

   Python 60 7