some experiments with training and fine-tuning decision transformer

Python3 port of the official PyTorch implementation of TD3 for OpenAI gym tasks

Sparse environment for MuJoCo suite (v2 and v3)

Dockerfile for mujoco200 environment. Visualization via X server.

This repository contains the scripts and results of running HER+DDPG experiments on the shadow dexterous hand.

Implementation of the deep-RL algorithm DDPG.

An Apptainer/Singularity container for using MuJoCo-mjx on GPU.

Physics simulator for Pupper robot

Wrappers for environments from Mujoco Gym and dm_control that make them deterministic

Code of the article "Benchmarking the Sim-to-Real Gap in Cloth Manipulation"

Training a Donkey Car to drive/park using Imitation Learning

MuJoCo Humanoid Maze Env

Caution: Beware of Dogs!

The Docker image for the isolated Mujoco environment

This is the development repo of Virtual Reality rendering with Mujoco Physics Environment with help of OpenVR SDK and HTC Vive HMD hardware. On top of it, a PubSub socket-based communication is introduced using the ZMQ library. Using this PubSub communication any application outside the Mujoco application can be used to operate actuators inside …

Comparison between use of arms and w/o it using MPC

PPO implementation for controlling a humanoid in Gymnasium's Mujoco environment, featuring customizable training scripts and multi-environment parallel training.

Implementation of the deep-RL algorithm DDPG.