Stars
A reinforcement learning codebase focusing on the emergence of cooperation and alignment in multi-agent AI systems.
Simple single-file baselines for Q-Learning in pure-GPU setting
Research Code for "ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL"
A python package for end-to-end geospatial machine learning using multispectral earth observation data such as NASA HLS and ESA Sentinel-2.
RewardBench: the first evaluation tool for reward models.
🏛️A research-friendly codebase for fast experimentation of single-agent reinforcement learning in JAX • End-to-End JAX RL
SKAI is a machine learning based tool for performing automatic building damage assessments on aerial imagery of disaster sites.
JAX-accelerated Meta-Reinforcement Learning Environments Inspired by XLand and MiniGrid 🏎️
Benchmarking RL for POMDPs in Pure JAX [Code for "Structured State Space Models for In-Context Reinforcement Learning" (NeurIPS 2023)]
BenchMARL is a library for benchmarking Multi-Agent Reinforcement Learning (MARL). BenchMARL allows to quickly compare different MARL algorithms, tasks, and models while being systematically ground…
🧭 COMPASS: Combinatorial Optimization with Policy Adaptation using Latent Space Search
Efficient baselines for autocurricula in JAX.
Datasets with baselines for offline multi-agent reinforcement learning.
⚡ Flashbax: Accelerated Replay Buffers in JAX
🪐 The Sebulba architecture to scale r 9928 einforcement learning on Cloud TPUs in JAX
Foundation Models for Genomics & Transcriptomics
A tool for aggregating and plotting MARL experiment data.
High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)
Code of the paper: Debiasing Meta-Gradient Reinforcement Learning by Learning the Outer Value Function
Multi-Robot Warehouse (RWARE): A multi-agent reinforcement learning environment
🧬 ManyFold: An efficient and flexible library for training and validating protein folding models
🌺 Population-Based Reinforcement Learning for Combinatorial Optimization
[NeurIPS 2022] Open source code for reusing prior computational work in RL.
A categorised list of Multi-Agent Reinforcemnt Learning (MARL) papers
🕹️ A diverse suite of scalable reinforcement learning environments in JAX
Notebooks for the Practicals at the Deep Learning Indaba 2022.