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

Recurrent Policies for Handling Partially Observable Environments

An implementation of Proximal Policy Optimization using TensorFlow. Tested on the OpenAI Gym car racing environment.

Training PPO agents in OpenAI Gym and PyBullet environments.

An autonomous agent that learns to play Atari Bowling using Reinforcement Learning and Proximal Policy Optimization

You can see a reference for Books, Articles, Courses and Educational Materials in this field. Implementation of Reinforcement Learning Algorithms and Environments. Python, OpenAI Gym, Tensorflow.

Implement PPO to solve Crawler problem in Unity

An implementation from the state-of-the-art family of reinforcement learning algorithms Proximal Policy Optimization using normalized Generalized Advantage Estimation and optional batch mode training. The loss function incorporates an entropy bonus.

XOXO² - Use Reinforcement Learning to train agent to play U_T-T-T.

A pytorch project to easily run experiments on OpenAI's Procgen Benchmark

Modular Deep RL infrastructure in PyTorch

Repositorio para el contenido relativo al trabajo de fin de máster desarrollado en el Máster de Inteligencia Artificial de la Universidad Internacional de La Rioja (UNIR).

This repository contains my assignment solutions for the Deep Reinforcement Learning course (430.729_003) offered by Seoul National University (Spring 2020).

A custom Gym environment for a Rock-Paper-Scissors game, where a reinforcement learning agent and a CNN model are trained, evaluated, and compared using Ray RLlib and TensorFlow.

Apply major Reinforcement Learning algorithms (DQN,PPO,A2C) to CarRacing-v0 from GymAI environment.

Training a PPO to balance a pendulum in a fully observable environment.

Noise-Adaptive Driving Assistance System (NADAS) using Deep Reinforcement Learning, State-Estimation & State Representation

AI agent learns to walk, run, hop and crawl with out any given data using proximal policy optimisation.

Reinforcement learning agent for playing Flappy Bird, as part of a university project