A car agent that has been trained using reinforcement learning to complete successful laps on a scaled-down version of the Circuit de Barcelona-Catalunya.

PPO.NETv2 is an implementation of Proximal Policy Optimization (PPO) using TensorFlow with comments in Portuguese. The environment used is CartPole-v0 from OpenAI Gym.

An implementation of the Proximal Policy Optimization (PPO) algorithm. This implementation is based on the example available on the official Keras website. The goal of this project is to provide a .NET-based solution for running PPO algorithms.

A simple demo showing asteroids with ML-Agents

Deep Reinforcement Learning techniques (PPO) applied to Swarm Robotics, focusing on defining stimulating environments and communication patterns in Search and Rescue scenario

Questo progetto Unity utilizza ML-Agents (PPO) per addestrare un agente veicolare in una città appartenente al pacchetto di SyntyStudios POLYGON - City Pack. L'agente cerca di: Schivare i gatti; seguire la segnaletica orizzontale; mantenere la corsia di sinistra; effettuare parcheggi nel punto di interesse più vicino.

Final task for my Reinforcement Learning class in Deusto. The research paper discuss examples of using ML-Agents toolkit of Unity. Paper is avaible at:

Reinforcement Learning - Route Optimization with Unity - ML-agents

A comparison between Reinforcement and Imitation Learning techniques for Multi-Agent 3D Racing using sensor-based approaches.

Car game made with unity

Concept and development of a walking AT-ST Walker (Starwars) ML-agent.

🚤🏖️BOATS DO VZHHHHH BBBDROOM, BEEEEP, BEEEP, GNAA, HONK, VZHHHHHHHHHHHHHH🏖️🚤

Target Strike game is an unity based compititive game. This game is created for CS662 - Mobile VR & AI course offered at IIT Mandi. Here the source files are given.

An ML implementation of the popular game "World Hardest Game" in Unity3D with ML-Agents.

Multiple Reinforcement learning techniques on 3x3 TicTacToe

Use of reinforcement learning with PPO to train an Agent that can beat the first level of Donkey Kong

Proyecto de entrenamiento de modelos de IA con aprendizaje por refuerzo (reinforcement learning) en Unity. Corresponde al trabajo práctico grupal de la materia INTELIGENCIA ARTIFICIAL (9525) de la Facultad de Ingeniería de la Universidad de Buenos Aires. Link a la demo (el comportamiento de los agentes puede verse afectado de forma negativa):

Rocket landing AI using reinforcement learning [keyword][Reinforcement Learning, ppo algorithm, ML-Agent]

Unity Environments based on ML-agents for the Walker agent to perform various locomotion behaviors using reinforcement learning

Tank game to experiment with the Unity ML-Agents Toolkit