Popular GitHub Repositories for Stable Baselines3

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

Deep Reinforcement Learning for Robotic Grasping from Octrees

OpenAI Gym environment solutions using Deep Reinforcement Learning.

Deep Reinforcement Learning based autonomous navigation for quadcopters using PPO algorithm.

This repository contains an application using ROS2 Humble, Gazebo, OpenAI Gym and Stable Baselines3 to train reinforcement learning agents for a path planning problem.

SocialGym 2: A lightweight benchmark and simulator for multi-robot social navigation using ROS and the OpenAI gym.

My implementation of a reinforcement learning model using Stable-Baselines3 to play the NES Super Mario Bros.

Implementation of Jump-Start Reinforcement Learning (JSRL) with Stable Baselines3

stable-baselines3 reinforcement learning on SUMO traffic light system

Data Center Environment and Reinforcement Learning (RL) Control

Study on the application of reinforcement learning to the management of a traffic light intersection.

Automated stock trading strategy using deep reinforcement learning and recurrent neural networks

Python package implementing task generators, traditional and ML-based scheduling algorithms, and assessment tools.

Building autonomous driving system by using CARLA simulator

Dockerized Container Architecture for Parallel Training of CARLA Gym Environments

Proximal Policy Optimization with Model-Agnostic Meta-Learning for Battery Energy Storage System Management in a Multi-Microgrid

Hybrid Action PPO in stable-baselines3

A collection of my implemented RL agents for games like Pacman, Pong, SpaceInvaders, Frozenlake, Taxi, Pixelcopter, Pyramids and a lot more by implementing various DRL algorithms using gym, unity-ml, pygame, sb3, rl-zoo and pandagym libraries. To see more advanced & interesting agents, please visit below link:

Implementing a new environment in Gymnasium for intelligent schduling

Study Model-Based Policy Optimization by varying the model estimator classes (e.g Decision Trees vs MLP)