{"id":16489618,"url":"https://github.com/alvinwan/bots-for-atari-games","last_synced_at":"2025-10-27T20:31:18.255Z","repository":{"id":89467718,"uuid":"119113919","full_name":"alvinwan/bots-for-atari-games","owner":"alvinwan","description":"Bots for Atari Games using Reinforcement Learning","archived":false,"fork":false,"pushed_at":"2019-04-06T23:26:28.000Z","size":26,"stargazers_count":12,"open_issues_count":0,"forks_count":9,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-06-11T20:56:04.270Z","etag":null,"topics":["atari-games","deep-learning","deep-reinforcement-learning","frozenlake","q-learning","reinforcement-learning","spaceinvaders"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/alvinwan.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2018-01-26T23:21:06.000Z","updated_at":"2023-11-14T11:06:03.000Z","dependencies_parsed_at":"2023-03-08T21:30:12.898Z","dependency_job_id":null,"html_url":"https://github.com/alvinwan/bots-for-atari-games","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/alvinwan/bots-for-atari-games","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alvinwan%2Fbots-for-atari-games","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alvinwan%2Fbots-for-atari-games/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alvinwan%2Fbots-for-atari-games/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alvinwan%2Fbots-for-atari-games/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/alvinwan","download_url":"https://codeload.github.com/alvinwan/bots-for-atari-games/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/alvinwan%2Fbots-for-atari-games/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":281336692,"owners_count":26483869,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-10-27T02:00:05.855Z","response_time":61,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["atari-games","deep-learning","deep-reinforcement-learning","frozenlake","q-learning","reinforcement-learning","spaceinvaders"],"created_at":"2024-10-11T13:44:44.715Z","updated_at":"2025-10-27T20:31:18.250Z","avatar_url":"https://github.com/alvinwan.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# [How to Build a Bot for Atari with OpenAI Gym](https://www.digitalocean.com/community/tutorials/how-to-build-atari-bot-with-openai-gym)\n\n**Want an in-person tutorial with step-by-step walkthroughs and explanations? See the corresponding AirBnb experience for both beginner and experienced coders alike, at [\"Build a Dog Filter with Computer Vision\"](https://abnb.me/UunXrPyqVO)** ([See the 45+ 5-star reviews](https://www.airbnb.com/users/show/87172280))\n\nThis repository includes all source code for the [tutorial on DigitalOcean](https://www.digitalocean.com/community/tutorials/how-to-build-atari-bot-with-openai-gym) with the same title, including:\n- Q-table based agent for FrozenLake\n- Simple neural network q-learning agent for FrozenLake\n- Least squares q-learning agent for FrozenLake\n- Code to use fully pretrained Deep Q-learning Network (DQN) agent on Space Invaders\n\n\u003e Each of these agents solve FrozenLake in 5000 episodes or fewer; whereas not in record time or even close to it, the agents are written with minimal tuning\n\ncreated by [Alvin Wan](http://alvinwan.com), January 2018\n\n![agent](https://user-images.githubusercontent.com/2068077/55676351-857eff80-5888-11e9-8fe6-8acf239f3e50.gif)\n\n# Getting Started\n\nFor complete step-by-step instructions, see the [tutorial on DigitalOcean](https://www.digitalocean.com/community/tutorials/how-to-build-atari-bot-with-openai-gym). This codebase was developed and tested using `Python 3.6`. If you're familiar with Python, then see the below to skip the tutorial and get started quickly:\n\n\u003e (Optional) [Setup a Python virtual environment](https://www.digitalocean.com/community/tutorials/common-python-tools-using-virtualenv-installing-with-pip-and-managing-packages#a-thorough-virtualenv-how-to) with Python 3.6.\n\n1. Navigate to the repository root, and install all Python dependencies.\n\n```\npip install -r requirements.txt\n```\n\n2. Navigate into `src`.\n\n```\ncd src\n```\n\n3. Download the Tensorflow model for SpaceInvaders, from Tensorpack's A3C-Gym sample.\n\n```\nmkdir models\nwget http://models.tensorpack.com/OpenAIGym/SpaceInvaders-v0.tfmodel -O models/SpaceInvaders-v0.tfmodel\n```\n\n4. Launch the script to see the Space Invaders agent in action.\n\n```\npython bot_6_dqn.py --visual\n```\n\n# How it Works\n\nSee the below resources for explanations of related concepts:\n\n- [\"Understanding Deep Q-Learning\"](http://alvinwan.com/understanding-deep-q-learning)\n- [\"Understanding the Bias-Variance Tradeoff\"](http://alvinwan.com/understanding-the-bias-variance-tradeoff)\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Falvinwan%2Fbots-for-atari-games","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Falvinwan%2Fbots-for-atari-games","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Falvinwan%2Fbots-for-atari-games/lists"}