{"id":18233388,"url":"https://github.com/grimmerk/alphago-zero-tictactoe-js","last_synced_at":"2025-06-27T03:33:09.606Z","repository":{"id":46201046,"uuid":"130539868","full_name":"grimmer0125/alphago-zero-tictactoe-js","owner":"grimmer0125","description":"A game framework based on AlphaZero/TensorFlow.js runs in browser to demonstrate tic-tac-toe AI game. Use a pre-trained model or train from scratch. Ported from suragnair/alpha-zero-general (Python)","archived":false,"fork":false,"pushed_at":"2023-01-04T02:49:57.000Z","size":5321,"stargazers_count":39,"open_issues_count":4,"forks_count":6,"subscribers_count":6,"default_branch":"master","last_synced_at":"2024-04-28T04:58:14.340Z","etag":null,"topics":["alphazero","browser","cnn","create-react-app","deep-learning","game","javascript","monte-carlo-tree-search","neural-network","numjs","reactjs","reinforcement-learning","semantic-ui","skip-resnet-implementation","tic-tac-toe","tictactoe"],"latest_commit_sha":null,"homepage":"","language":"JavaScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/grimmer0125.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}},"created_at":"2018-04-22T06:01:44.000Z","updated_at":"2024-04-03T04:44:32.000Z","dependencies_parsed_at":"2023-02-01T18:02:10.976Z","dependency_job_id":null,"html_url":"https://github.com/grimmer0125/alphago-zero-tictactoe-js","commit_stats":null,"previous_names":[],"tags_count":1,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/grimmer0125%2Falphago-zero-tictactoe-js","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/grimmer0125%2Falphago-zero-tictactoe-js/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/grimmer0125%2Falphago-zero-tictactoe-js/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/grimmer0125%2Falphago-zero-tictactoe-js/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/grimmer0125","download_url":"https://codeload.github.com/grimmer0125/alphago-zero-tictactoe-js/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":223016340,"owners_count":17074036,"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","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":["alphazero","browser","cnn","create-react-app","deep-learning","game","javascript","monte-carlo-tree-search","neural-network","numjs","reactjs","reinforcement-learning","semantic-ui","skip-resnet-implementation","tic-tac-toe","tictactoe"],"created_at":"2024-11-04T15:04:23.003Z","updated_at":"2025-04-03T19:31:08.414Z","avatar_url":"https://github.com/grimmer0125.png","language":"JavaScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# AlphaGo Zero Tictactoe JS\n\nTry it: https://grimmer.io/alphago-zero-tictactoe-js/. Google DeepMind AlphaGo uses enhancement learning and the algorithm is a composite of \n\n1. Policy Network\n2. Value Network\n3. Monte Carlo tree search (MCTS)\n\n## Installation\n\n```\nnpm install\n```\n\n### Dev\n\n```\nnpm start // build and launch its live dev web server.\n```\n\nAfter `npm start`, you can also use `VS Code` with `Debugger for Chrome` extension to debug.\n\n### TypeScript Support and Vite\n\nThis project has been migrated to TypeScript and now uses Vite! You can:\n\n```\nnpm run dev         # Start Vite development server\nnpm run start       # Alias for npm run dev\nnpm run build       # Build production bundle\nnpm run preview     # Preview production build\nnpm run typecheck   # Run TypeScript check without emitting files\nnpm run ts:watch    # Watch for TypeScript errors in real-time\n```\n\nSee [TYPESCRIPT.md](TYPESCRIPT.md) for more details on the TypeScript conversion.\n\n\n### Deployment \n\n```\nnpm run deploy\n```\n\n## Features and done itmes of todo list\n\n1. Ported the algorithms from [alpha-zero-general](https://github.com/suragnair/alpha-zero-general). Although its name is `alpha-zero-general`, it is based on AlphaGo Zero algorithm. \n\n2. Import pretrained models from [alpha-zero-general](https://github.com/suragnair/alpha-zero-general) and run alphago game algorithms on Browsers.\n`alpha-zero-general` is a project to supply general game AI training frameworks. You can extend that project and add yourself game rule codes and train AI model\nby using Python.\n\n## TODO\n\n1. ~~Fix bugs to train models by this JavaScript version project. It may be a TensorFlow.js bug. Maybe waitting for native TensorFlow Node.js binding is better than WebGL solution.~~\n2. ~~Add UI.~~\n3. Clean up. (50%)\n4. Use service worker for cpu heavy loading part.\n5. ~~Use TypeScript instead~~ (Done! See [TYPESCRIPT.md](TYPESCRIPT.md))\n\n## AlphaZero\n\nTo overcome some API limitation (Tensorflow.js export/save model/weights), so this JavaScript repo borrows one of the features of AlphaZero, **always accept trained model after each iteration without comparing to previous version**\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgrimmerk%2Falphago-zero-tictactoe-js","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fgrimmerk%2Falphago-zero-tictactoe-js","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fgrimmerk%2Falphago-zero-tictactoe-js/lists"}