Comparing different algorithm performances on Atari games such as Pong

Example Rainbow DQN implementation with ReLAx

2022 Spring Semester, Personal Project Research

Atari Centipede Game created by C. (C 实现 Atari 经典街机游戏《飞天蜈蚣》)

Breakout is an arcade game developed and published by Atari and released on May 13, 1976. It was created by Nolan Bushnell and Steve Bristov who where influenced by 1972 Atari arcade game Pong and build by Steve Wozniack.

In this project, we attempt to equip the agent with the recognition of basic components of an Atari game environment through curriculum learning—gleaned from human developmental psychology—and evaluate its performance. Our best agent was pre-trained on a carefully designed curriculum to learn to complete a new game 5x faster than regular agents.…

This repo contains the source code of Maze Escape, a 3 level maze game for the Atari 2600. You can find the compiled version here https://castesoftworks.itch.io/maze-escape

Rewrite of the original 1973 Space Race game developed by Atari in Java

A simple 2D pong game made with Pygame on Python 3.6. (See the readme for more details)

Replicating DeepMind experiments on Atari Games using Deep RL

6502 assembly development for Atari 2600 game console.

JavaScript based tracker application that exports compositions into assembly code for Paul Slocums Sequencer Kit for Atari 2600

Code associated with the paper "Ego Networks"

a board game for Atari ST

It is a project of exploring reinforcement-learning on Atari-Freeway game.

A convolutional net, re-inforcement learning model that plays Atari's Breakout

Deep Q-learning with TensorFlow

Asteroids Game in Javascript

This repository hosts Jupyter notebooks showcasing the training of Atari games using a variety of Deep Reinforcement Learning (RL) algorithms such as Proximal Policy Optimization (PPO), Deep Deterministic Policy Gradient (DDPG), Deep Q-Networks (DQN), Advantage Actor-Critic (A2C), and more.

Cowbell Hero for Atari ST