{"id":19287179,"url":"https://github.com/opendilab/di-1024","last_synced_at":"2025-04-13T03:56:02.057Z","repository":{"id":62100136,"uuid":"556653628","full_name":"opendilab/DI-1024","owner":"opendilab","description":"1024 + 深度强化学习（Deep Reinforcement Learning + 1024 Game/ 2048 Game)","archived":false,"fork":false,"pushed_at":"2024-07-23T10:36:08.000Z","size":1125,"stargazers_count":118,"open_issues_count":0,"forks_count":3,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-04-13T03:55:44.610Z","etag":null,"topics":["1024-game","2048","2048-game","deep-reinforcement-learning","javascript","python","reinforcement-learning"],"latest_commit_sha":null,"homepage":"https://opendilab.net/1024","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/opendilab.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":"2022-10-24T08:56:22.000Z","updated_at":"2025-04-04T02:05:49.000Z","dependencies_parsed_at":"2024-12-17T11:02:14.728Z","dependency_job_id":null,"html_url":"https://github.com/opendilab/DI-1024","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/opendilab%2FDI-1024","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/opendilab%2FDI-1024/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/opendilab%2FDI-1024/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/opendilab%2FDI-1024/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/opendilab","download_url":"https://codeload.github.com/opendilab/DI-1024/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248661709,"owners_count":21141450,"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":["1024-game","2048","2048-game","deep-reinforcement-learning","javascript","python","reinforcement-learning"],"created_at":"2024-11-09T22:05:36.530Z","updated_at":"2025-04-13T03:56:02.016Z","avatar_url":"https://github.com/opendilab.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# DI-1024：深度强化学习 + 1024游戏\r\n\r\n\u003e 1024 游戏有时也被称为 [2048](https://en.wikipedia.org/wiki/2048_(video_game))。\r\n\r\n是人机协作共同解密，还是人机对抗捕捉 AI 背后的的种种虫（Bug）。欢迎一起回味二的幂次方，体验极客瞬间~\r\n\r\nP.S. 路过记得点个 star ![stars - di-1024](https://img.shields.io/github/stars/opendilab/di-1024?style=social) ，持续更新ing。\r\n\r\nP.S.S. 想了解更多深度强化学习相关知识？快来 [DI-engine](https://github.com/opendilab/DI-engine) 和 [LightZero](https://github.com/opendilab/LightZero) 训练自己的智能体。\r\n\r\n\u003cdiv align=\"center\"\u003e\r\n    \u003ca href=\"https://github.com/opendilab/DI-1024\"\u003e\u003cimg width=\"500px\" height=\"auto\" src=\"https://github.com/opendilab/DI-1024/blob/main/assets/di1024_demo.png\"\u003e\u003c/a\u003e\r\n\u003c/div\u003e\r\n\r\n# News\r\n[WeChat] [今日忌加班，宜玩1024](https://opendilab.net/1024)\r\n\r\n# 使用指南\r\n\r\n- 在线网页版试玩 -\u003e [传送门](https://opendilab.net/1024)\r\n\r\n# 训练指南\r\n\r\n先用以下命令安装依赖的包：\r\n\r\n```bash\r\npip3 install -r requirements.txt\r\n```\r\n\r\n### MuZero 智能体训练\r\n\r\n在 1024 环境上快速训练一个 [MuZero](https://github.com/opendilab/LightZero/blob/main/lzero/policy/muzero.py) 智能体：\r\n\r\n```bash\r\ncd DI-1024\r\npython3 -u agent/config/muzero_2048_config.py\r\n```\r\n\r\n### StochasticMuZero 智能体训练\r\n\r\n在 1024 环境上快速训练一个 [StochasticMuZero](https://github.com/opendilab/LightZero/blob/main/lzero/policy/stochastic_muzero.py) 智能体：\r\n\r\n```bash\r\ncd DI-1024\r\npython3 -u agent/config/stochastic_muzero_2048_config.py\r\n```\r\n\r\n### 训练曲线\r\n\r\n![img.png](assets/2048_benchmark.png)\r\n\r\n\r\n# 更新计划\r\n\r\n- [x] 网页在线版试玩\r\n- [x] 完整强化学习训练样例\r\n- [x] 结合 Stochastic MuZero 的最强 1024 游戏智能体\r\n- [ ] 提供可供本地试玩的模型权重\r\n- [ ] 设计更有趣的人机对抗算法\r\n\r\n# 致谢\r\n- JS 前端部分主要基于 https://github.com/xwjdsh/2048-ai 进行魔改，请大家也多多支持这个 repo \r\n\r\n\r\n# License\r\nDI-1024 is released under the Apache 2.0 license.\r\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fopendilab%2Fdi-1024","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fopendilab%2Fdi-1024","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fopendilab%2Fdi-1024/lists"}