A toolkit for practical Human-AI cooperation research

Multi Agent Traffic Scenario Gym: A scenario-based training and evaluation framework for CARLA.

LLM vulnerability scanner

Multi-Agent Reinforcement Learning with JAX

Find unused, missing and transitive dependencies in a Python project.

♟️ Vectorized RL game environments in JAX

High-quality single-file implementations of SOTA Offline and Offline-to-Online RL algorithms: AWAC, BC, CQL, DT, EDAC, IQL, SAC-N, TD3+BC, LB-SAC, SPOT, Cal-QL, ReBRAC

Reinforcement Learning Environments for Sustainable Energy Systems

Non-cooperative satellite operations challenge problems implemented in the Kerbal Space Program game engine

Scalene: a high-performance, high-precision CPU, GPU, and memory profiler for Python with AI-powered optimization proposals

The Arcade Learning Environment (ALE) -- a platform for AI research.

Generative Agents: Interactive Simulacra of Human Behavior

Streamlining reinforcement learning with RLOps. State-of-the-art RL algorithms and tools.

High-quality single-file implementations of SOTA Offline and Offline-to-Online RL algorithms: AWAC, BC, CQL, DT, EDAC, IQL, SAC-N, TD3+BC, LB-SAC, SPOT, Cal-QL, ReBRAC

A training framework for Stable Baselines3 reinforcement learning agents, with hyperparameter optimization and pre-trained agents included.

[NeurIPS 2023] Reflexion: Language Agents with Verbal Reinforcement Learning

AI Observability & Evaluation

Minetest is an open source voxel game engine with easy modding and game creation

Baseline agents for Minetest tasks.

Multithreaded Python without the GIL

Clean PyTorch implementations of imitation and reward learning algorithms

An engine for high performance multi-agent environments with very large numbers of agents, along with a set of reference environments

Animation engine for explanatory math videos

Multi-Objective Reinforcement Learning algorithms implementations.

[NeurIPS 2023] Tree of Thoughts: Deliberate Problem Solving with Large Language Models

Multi-objective Gymnasium environments for reinforcement learning

JAX and PZ RL envs + algorithms for swarms of CrazyFlies

🤖 AgentVerse 🪐 is designed to facilitate the deployment of multiple LLM-based agents in various applications, which primarily provides two frameworks: task-solving and simulation