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.

training an agent to navigate a 2D space

Water resources exploring and reservoir operations Using Multi-Agent Deep Reinforcement Learning.

Reinforcement learning for crawling robot

Repository with all source files relating to the 6CCE3EEP Final Year Project titled "Self Parking with Reinforcement Learning." The project was implemented using Python, and used PyGame, OpenAI Gym, and the Stable Baselines-3 libraries in order to implement a Proximal Policy Optimisation (PPO) algorithm.

This repository hosts the code and resources for a comprehensive study on optimizing greenhouse conditions using Reinforcement Learning algorithms such as PPO, A2C, and SAC. For detailed results, explanation of the environments, and the algorithms, please refer to the accompanying report.

Program made for my bachelor's thesis. It compares efficency of different reinforcement learning algorithms at playing Minesweeper.

Locomotion and Posture Control of Wheeled Bipedal using Reinforcement Learning Techniques

Bachelor's Thesis Sergio Vittorio Zambelli - 2023/2024

This repository contains the implementation of a wide variety of Reinforcement Learning Projects in different applications of Bandit Algorithms, MDPs, Distributed RL and Deep RL. These projects include university projects and projects implemented due to interest in Reinforcement Learning.

Reinforce learning gym for Elden Ring, based on gymnaium and stable baseline3, PPO

State Representations as Incentives for Reinforcement Learning Agents: A Sim2Real Analysis on Robotic Grasping

A testbed for exploring reinforcement learning & basketball strategy

This is a GYM environment for the PySuperTuxKart game. It is designed for Reinforcement Learning (RL) applications, particularly for educational purposes. The repository also includes examples of using this environment with Stable Baselines 3 (SB3)'s PPO algorithm.

Pybullet Gymnasium Environment for WERDNA

A hybrid collision avoidance system combining Deep Reinforcement Learning with Model Predictive Control, designed for autonomous vehicles in CARLA to navigate scenarios with stationary obstacles.

The project presents a drone obstacle avoidance system using Microsoft AirSim and the DDPG algorithm, training drones with LIDAR and depth sensors for improved real-time navigation. It compares the implementation of DDPG algorithm with different sensors and their combination.

Application of reinforcement learning to the management of traffic light intersection

An end-to-end (E2E) reinforcement learning model for autonomous vehicle collision avoidance in the CARLA simulator, using a recurrent PPO algorithm for dynamic control. The model processes RGB camera inputs to make real-time acceleration and steering decisions.

This repo contains our project for CPE 800 which focuses on reinforcement learning for stock prediction