Pinned Loading

1. facebookresearch/llm-speedrunner facebookresearch/llm-speedrunner Public

   The Automated LLM Speedrunning Benchmark measures how well LLM agents can reproduce previous innovations and discover new ones in language modeling.

   Jupyter Notebook 112 8

2. facebookresearch/minimax facebookresearch/minimax Public

   Efficient baselines for autocurricula in JAX.

   Python 201 17

3. facebookresearch/dcd facebookresearch/dcd Public archive

   Implementations of robust Dual Curriculum Design (DCD) algorithms for unsupervised environment design.

   Python 137 32

4. facebookresearch/level-replay facebookresearch/level-replay Public archive

   This code implements Prioritized Level Replay, a method for sampling training levels for reinforcement learning agents that exploits the fact that not all levels are equally useful for agents to le…

   Python 92 16

5. learning-to-communicate-pytorch learning-to-communicate-pytorch Public

   Learning to Communicate with Deep Multi-Agent Reinforcement Learning in PyTorch

   Python 358 80

6. facebookresearch/minihack facebookresearch/minihack Public archive

   MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research

   Python 504 66