Dynamics and Domain Randomized Gait Modulation with Bezier Curves for Sim-to-Real Legged Locomotion.

ns3-gym - The Playground for Reinforcement Learning in Networking Research

A Python3 NES emulator and OpenAI Gym interface

Framework for developing OpenAI Gym robotics environments simulated with Ignition Gazebo

A Repository with C++ implementations of Reinforcement Learning Algorithms (Pytorch)

Deep Developmental Reinforcement Learning

Decentralized Multi-Agent Exploration on ROS with Distributed Deep Reinforcement Learning using A3C Algorithm

gym tcp api

A C++ implementation of the asynchronous advantage actor-critic (A3C) algorithm

VANET simulation using Veins-Gym to combine Veins with Reinforcement Learning

Anomalous versions of OpenAI Gym and PyBullet3 environments

C++ wrappers of OpenAI-Gym environments

Implementation of Reinforcement learning algortihm in HTTP Adaptive Streaming (HAS) over NS3

Deep Reinforcement Learning applied to the control of a 3 DOF robot arm using OpenAI Gym and Gazebo. Done as part of the Udacity Robotics Nanodegree.

C++17 OpenAI gym

This repository contains code for simulating coupled motion of rigid ball and fluid in 2D and this is used as an environment in Gym to train a controller to balance the ball in air.

Active-flow-control (AFC) environments developed using the Gym-preCICE adapter.

Decentralized Multi-Agent Exploration on ROS with Distributed Deep Reinforcement Learning using A3C Algorithm

The playground for reinforcement learning in networking research with SUMO integration.

C++ implementation of the continuous LunarLander environment.