Reinforcement learning algorithms implemented to learn to play Super Mario Bros.

Reinforcement learning algorithms and solved gym environments.

Exercises and projects from Udacity's Nanodegree

Yet another deep reinforcement learning

Deep Q-Learning algorithms to solve LunarLander-v2.

This project uses Deep Reinforcement Learning to solve the Lunar Lander environment of the OpenAI-Gym

Various Deep RL models applied to Super Mario Bros

Snake Game solved using Dueling DQN and Dueling Double DQN

Generative Adversial Imitation Learning (GAIL) an inverse reinforcement learning algorithm

Reinforcement learning agent that solves a 2x2 Rubik's cube

Develop an AI player of Atari Skiing with deep reinforcement learning

My reproduction of various reinforcement learning algorithms (DQN variants, A3C, DPPO, RND with PPO) in Tensorflow.

Deep Reinforcement Learning with Custom Environment

Basic code for reinforcement learning and small programs.

This is a Deep Reinforcement Learning solution for the Lunar Lander problem in OpenAI Gym using dueling network architecture and the double DQN algorithm.

Reinforcement learning algorithms in poker games

Lunar Lander envitoment of gymnasium solved using Double DQN and D3QN

A Torch Based RL Framework for Rapid Prototyping of Research Papers

A revisit of the classic Super Mario Bros (1985) for the NES, this project explores the possibilities of embodied artificial intelligence through reinforcement learning (RL), by training Double Q-Network (DQN) and Dueling Q-Network (DDQN) agents.