A QoE-Oriented Computation Offloading Algorithm based on Deep Reinforcement Learning for Mobile Edge Computing

A Torch Based RL Framework for Rapid Prototyping of Research Papers

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

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

Lunar Lander envitoment of gymnasium solved using Double DQN and D3QN

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

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

Exercises and projects from Udacity's Nanodegree

Reinforcement learning algorithms and solved gym environments.

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

Various Deep RL models applied to Super Mario Bros

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

Deep Reinforcement Learning with Custom Environment

Yet another deep reinforcement learning

Develop an AI player of Atari Skiing with deep reinforcement learning

Reinforcement learning algorithms in poker games

Deep Q-Learning algorithms to solve LunarLander-v2.

Basic code for reinforcement learning and small programs.

Snake Game solved using Dueling DQN and Dueling Double DQN