dm-control 开源项目推荐（33 个）

sail-sg /envpool

用于一般RL环境的基于C++的高性能并行环境执行引擎（vectorized env）。

denisyarats /pytorch_sac

PyTorch implementation of Soft Actor-Critic (SAC)

denisyarats /drq

DrQ: Data regularized Q

MishaLaskin /rad

RAD: Reinforcement Learning with Augmented Data

ian-chuang /Manipulator-Mujoco

Base Mujoco Gymnasium environment for easily controlling any robot arm with operational space control. Built with dm-control PyMJCF for easy configuration.

denisyarats /pytorch_sac_ae

PyTorch implementation of Soft Actor-Critic + Autoencoder(SAC+AE)

microsoft /MoCapAct

A Multi-Task Dataset for Simulated Humanoid Control

denisyarats /dmc2gym

OpenAI Gym wrapper for the DeepMind Control Suite

pokaxpoka /sunrise

SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learning

nicklashansen /policy-adaptation-during-deployment

Training code and evaluation benchmarks for the "Self-Supervised Policy Adaptation during Deployment" paper.

denisyarats /proto

Proto-RL: Reinforcement Learning with Prototypical Representations

zuoxingdong /dm2gym

Convert DeepMind Control Suite to OpenAI gym environments.

dvalenciar /ReinforceUI-Studio

ReinforceUI-Studio. A Python-based application designed to simplify the configuration and monitoring of RL training processes. Supporting MuJoCo, OpenAI Gymnasium, and DeepMind Control Suite. Algorithms included: CTD4, DDPG, DQN, PPO, SAC, TD3, TQC

Soltanilara /av-aloha

Code for the paper: "Active Vision Might Be All You Need: Exploring Active Vision in Bimanual Robotic Manipulation"

UtkarshMishra04 /pixel-representations-RL

This repository is a collection of widely used self-supervised auxiliary losses used for learning representations in reinforcement learning.

mehranagh20 /wimle

Codebase for WIMLE: Uncertainty-Aware World Models for Reinforcement Learning (ICLR 2026)

yunke-wang /gail_atari

PyTorch Implementation of Visual GAIL in Atari Games

JChunX /fetch_freight_mujoco

Mujoco xml model for the Fetch Robotics Freight mobile base + Panda arm

sharif1093 /digideep

A Deep Reinforcement Learning (DeepRL) package for RL algorithm developers.

imgeorgiev /dmc2gymnasium

Gymnasium integration for the DeepMind Control (DMC) suite