This repository contains model-free deep reinforcement learning algorithms implemented in Pytorch

Simple renderer for use with MuJoCo (>=2.1.2) Python Bindings.

This repository contains the implementation for the paper - Exploration via Hierarchical Meta Reinforcement Learning.

Iterative LQG for a couple of MuJoCo models

Multi-rotor Gym

Model-based Policy Gradients

Simple-to-use-and-extend implementation of the DeepMimic Approach using the MuJoCo Physics Engine and Stable Baselines 3, mainly for locomotion tasks.

PPO implementation of Humanoid-v2 from Open-AI gym

The code corresponding to the paper "Improving Sample Efficiency of Deep Reinforcement Learning for Bipedal Walking".

Soft robotics in MuJoCo

Manipulation Demo using mujoco-py

Sparse environment for MuJoCo suite (v2 and v3)

Turn STL formulas into maps and planed paths, control robots with DRL controllers.

Implementation of Multiplicative Compositional Policies (MCP)

Reinforcement Learning CS6700 Course Capstone Project

Code from "How useful is quantilization for mitigating specification-gaming?"

Installation MuJoCo on Ubuntu 16.04 with NVIDIA GPU

Training robots to play soccer

Simple renderer for use with MuJoCo (2.2.x) Python Bindings, on M1 Mac.