This repository contains most of pytorch implementation based classic deep reinforcement learning algorithms, including - DQN, DDQN, Dueling Network, DDPG, SAC, A2C, PPO, TRPO. (More algorithms are still in progress)

JAX implementation of deep RL agents with resets from the paper "The Primacy Bias in Deep Reinforcement Learning"

Atari 2600 Open-source System-on-Chip (SoC)

An implementation of Deep Q-Learning from Demonstrations (DQfD) for playing Atari 2600 video games

A collection of Deep Reinforcement Learning algorithms implemented in tensorflow. Very extensible. High performing DQN implementation.

An AI that plays Atari 2600 Pong. Trained with reinforcement learning using OpenAI Gym and Keras

👾 My solutions to OpenAI Gym Reinforcement Learning problems.

A PyTorch implementation of reinforcement lerning algorithms (DQN, DDQN, Prior DDQN, Distributed) based on ray

🍻 A simple implementation of dqn algorithm using pytorch

I used Cross Entropy methods as an alternative to reinforcement learning methods to search policy space for the optimal policy where there is no assumption about the structure of the problem for both continuous and discrete space tasks in OpenAI gym.

Code from "How useful is quantilization for mitigating specification-gaming?"

An implementation of a Deep Reinforcement Learning model that trains an agent to play Atari 2600 games.

[AAAI-22] Curiosity-based objective for exploration with reinforcement learning in state-based and vision-based environments.

Rainbow, IQN on atari games

Playfield Pixel Perfect Pro: The ultimate Atari 2600 playfield designer

An Atari 2600 TIA chip controller

A deep-q reinforcement learning agent built from the ground up in Python to play Atari 2600 games based on the work published by DeepMind.

Bot to play River Raid game from Atari. Practial work of Computational Robotics subject at UFSJ.