This repository hosts Jupyter notebooks showcasing the training of Atari games using a variety of Deep Reinforcement Learning (RL) algorithms such as Proximal Policy Optimization (PPO), Deep Deterministic Policy Gradient (DDPG), Deep Q-Networks (DQN), Advantage Actor-Critic (A2C), and more.

⛰ Reinforcement learning model trying to make car reach to top of mountain

🎲 Match 3 Agent using PPO

Multi-agent RL environment for a pikachu-volleyball game based on Pettingzoo.

Lunar Lander envitoment of gymnasium solved using Double DQN and D3QN

RealROS is an open-source Python framework that seamlessly integrates with ROS (Robot Operating System) to create real-world robotics environments tailored for reinforcement learning (RL) applications. This modular framework simplifies RL development, enabling real-time training with physical robots

MultiROS is an open-source ROS based simulation environment designed for concurrent deep reinforcement learning. It provides a flexible and scalable framework for training and evaluating reinforcement learning agents for complex robotic tasks.

An API standard for multi-agent reinforcement learning environments, with popular reference environments and related utilities

PyBullet Gymnasium environments for single and multi-agent reinforcement learning of quadcopter control

A comprehensive framework for reinforcement learning in robotics, which allows users to train their robots in both simulated and real-world environments.

A standard format for offline reinforcement learning datasets, with popular reference datasets and related utilities

Unified Reinforcement Learning Framework

(Yet another) Reinforcement Learning repository that aims to implement and benchmark various RL algorithms

⚡⚡ Lightning Fast (~300TPS) Reinforcement Learning environment on latest Minecraft 🏝️

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

A toolkit for auto-generation of OpenAI Gym environments from RDDL description files.

Autonomous driving episode generation for the Carla simulator in a gym environment. This framework makes it easy to create driving scenarios to train/test the agent.

A collection of robotics simulation environments for reinforcement learning

A collection of environments and reference agents for planning and reinforcement learning research in partially observable, multi-agent environments.

A Python program to play the first level of Donkey Kong Country (SNES, 1996), Jungle Hijinks, using the genetic algorithm NEAT (NeuroEvolution of Augmenting Topologies) and Gymnasium, a maintained fork of OpenAI's Gym.