This project implements an agent for playing the SonicTheHedgehog2 game from a ROM file using the Proximal Policy Optimization (PPO) algorithm from the stablebaselines3 library. The agent is trained to learn the optimal actions to take at each step in the game in order to complete the level and maximize the score.

Distributed training for RL algo on pytorch

🍄​ Reinforcement Learning agent for Super Mario Bros

Autonomous 1:10 race car with a reinforcement learning based approach

Implementation of RL algorithms using the stable baselines library

A custom OpenAI gym environment for training Tic-Tac-Toe agents with Stable-Baselines3

Pilotage d'un pendule de Furuta avec un Raspberry PI

Analyzing policy entropy of reinforcement learning agents

Implementation of T-REX and D-REX Inverse Reinforcement Learning (IRL) algorithm for learning form suboptimal demonstrations

In this project I pass through the principles and concepts of Reinforced Learning and I trained an agent to manage the energy resources

A bot largely inspired by Necto and trained using novel rewards functions

Evaluate Feature extraction in the reinforcement learning, with environements from OpenAi gym, and policies from stable-baselines3

In this project, I created an agent using the PPO algorithm from stable baselines3 to complete a task in the LunarLander environment. The agent was trained using reinforcement learning techniques to maximize its performance in the task. The resulting model was able to achieve a high level of success in the LunarLander environment.

Custom TicTacToe openai-gym enviroment for PPO RL-agent

Obstacle avoidance agent in a custom Gym environment

Tutorial from Nicholas Renotte : https://www.youtube.com/watch?v=2eeYqJ0uBKE

Git repository for LQR and Reinforcement Learning labs. Code for modeling human movement and solving optimization using PPO algorithm.

Example of Reinforcement Learning Environment on Minecraft with Stable-Baselines3 and CraftGround

Clean and flexible implementation of PPO (built on top of stable-baselines3)