AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)

Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)

PyTorch implementation of DQN, AC, ACER, A2C, A3C, PG, DDPG, TRPO, PPO, SAC, TD3 and ....

A Python toolbox for performing gradient-free optimization

Check out the new game server:

Code for a multi-agent particle environment used in the paper "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments"

Spatial Temporal Graph Convolutional Networks (ST-GCN) for Skeleton-Based Action Recognition in PyTorch

Implementations of IQL, QMIX, VDN, COMA, QTRAN, MAVEN, CommNet, DyMA-CL, and G2ANet on SMAC, the decentralised micromanagement scenario of StarCraft II

Vector Quantized VAEs - PyTorch Implementation

Really Fast End-to-End Jax RL Implementations

Reinforcement Learning environments for Traffic Signal Control with SUMO. Compatible with Gymnasium, PettingZoo, and popular RL libraries.

Honor of Kings AI Open Environment of Tencent

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

Concise pytorch implements of MARL algorithms, including MAPPO, MADDPG, MATD3, QMIX and VDN.

The release codes of LA-MCTS with its application to Neural Architecture Search.

Level-based Foraging (LBF): A multi-agent environment for RL

Learning Invariant Representations for Reinforcement Learning without Reconstruction

(NeurIPS 2023) ChessGPT - Bridging Policy Learning and Language Modeling

[NeurIPS 2021] CDS achieves remarkable success in challenging benchmarks SMAC and GRF by balancing sharing and diversity.

Code for "World Model as a Graph: Learning Latent Landmarks for Planning" (ICML 2021 Long Presentation)

The official implementation of "Transformer in Transformer as Backbone for Deep Reinforcement Learning"

The code for AAMAS2022 《GCS: Graph-based Coordination Strategy for Multi-Agent Reinforcement Learning》

PyTorch code accompanying the paper "Landmark-Guided Subgoal Generation in Hierarchical Reinforcement Learning" (NeurIPS 2021).

Source code of the SHADE with Iterative Local Search, an algorithm specially designed for for real-parameter optimization with high dimensionalidad (Large-Scale Global Optimization)

Official implementation of NeurIPS22 paper “Multi-agent Dynamic Algorithm Configuration”

This repository is an implementation of "MASER: Multi-Agent Reinforcement Learning with Subgoals Generated from Experience Replay Buffer" accepted to ICML 2022.