mujoco

Multi-Joint dynamics with Contact. A general purpose physics simulator.

An elegant PyTorch deep reinforcement learning library.

Google DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.

PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO), Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR) and Generative Adversarial Imitation Learning (GAIL).

OpenDILab Decision AI Engine. The Most Comprehensive Reinforcement Learning Framework B.P.

A collection of high-quality models for the MuJoCo physics engine, curated by Google DeepMind.

Reinforcement Learning Coach by Intel AI Lab enables easy experimentation with state of the art Reinforcement Learning algorithms

Collections of robotics environments geared towards benchmarking multi-task and meta reinforcement learning

Real-time behaviour synthesis with MuJoCo, using Predictive Control

C++-based high-performance parallel environment execution engine (vectorized env) for general RL environments.

MyoSuite is a collection of environments/tasks to be solved by musculoskeletal models simulated with the MuJoCo physics engine and wrapped in the OpenAI gym API.

XuanCe: A Comprehensive and Unified Deep Reinforcement Learning Library

Python library for Reinforcement Learning.

The Fastest Deep Reinforcement Learning Library

Python inverse kinematics based on MuJoCo

Training a humanoid robot for locomotion using Reinforcement Learning

Unified Reinforcement Learning Framework

A fully open-source humanoid arm for physical AI research and deployment in contact-rich environments.

A collection of robotics simulation environments for reinforcement learning

[CoRL '23] Dexterous piano playing with deep reinforcement learning.