{"id":17652284,"url":"https://github.com/zyxue/rljs","last_synced_at":"2026-05-16T17:41:50.073Z","repository":{"id":141946560,"uuid":"84027808","full_name":"zyxue/rljs","owner":"zyxue","description":"RLjs currently serves as an interactive playground for learning reinforcement learning.","archived":false,"fork":false,"pushed_at":"2019-01-07T20:02:10.000Z","size":1475,"stargazers_count":3,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-02-05T10:50:21.627Z","etag":null,"topics":["agent","algorithm","policy-iteration","q-learning","react","reinfrocement-learning","rl-algorithms","value-iteration"],"latest_commit_sha":null,"homepage":"https://rljs.herokuapp.com/","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/zyxue.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.txt","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":"2017-03-06T03:53:54.000Z","updated_at":"2020-06-24T20:23:11.000Z","dependencies_parsed_at":"2023-03-13T09:15:17.333Z","dependency_job_id":null,"html_url":"https://github.com/zyxue/rljs","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/zyxue%2Frljs","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zyxue%2Frljs/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zyxue%2Frljs/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/zyxue%2Frljs/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/zyxue","download_url":"https://codeload.github.com/zyxue/rljs/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246296583,"owners_count":20754632,"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":["agent","algorithm","policy-iteration","q-learning","react","reinfrocement-learning","rl-algorithms","value-iteration"],"created_at":"2024-10-23T11:46:27.753Z","updated_at":"2025-10-08T00:43:11.626Z","avatar_url":"https://github.com/zyxue.png","language":"JavaScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# RLjs\n\n**RLjs** is forked from [REINFORCEjs](https://github.com/karpathy/reinforcejs)\nby [Andrej Karpathy](http://cs.stanford.edu/people/karpathy/), but more\nmodualized with [React](https://facebook.github.io/react/)\nin [ES2015/ES6](https://babeljs.io/learn-es2015/). It tries to serve mainly as a\nplayground for learning reinforcement learning (RL) related algorithms. The two\nmain parts are:\n\n1. The agents as\n   in\n   [`src/lib/agents/`](https://github.com/zyxue/reinforcejs/tree/master/src/lib/agents),\n   which implement key RL algorithms such as dynamic\n   programming([Chapter 4](https://webdocs.cs.ualberta.ca/~sutton/book/ebook/node40.html)),\n   Sarsa, Q-Learning\n   ([Chapter 6](https://webdocs.cs.ualberta.ca/~sutton/book/ebook/node60.html),\n   [Chapter 7](https://webdocs.cs.ualberta.ca/~sutton/book/ebook/node72.html)).\n1. The grid world which is taken as the example to illustrate how different\n   agents/RL algorithms work.\n\nCurrently, only tabular methods have been covered. Approximation methods are\nplanned to be developed developed in the future.\n\nThe draft app is available at https://rljs.herokuapp.com/.\n\nThere is also another repo for hosting machine-learning related notebooks I\ncreated when learning/implementing algorithms at\nhttps://github.com/zyxue/sutton-barto-rl-exercises.\n\nA screenshot\n\n\u003cimg src=\"screenshot.png\" alt=\"screenshot\"\u003e\n\n## Setup\n\nThe development setup is adopted from\n[create-react-app](https://github.com/facebookincubator/create-react-app).\n\n```\ngit clone git@github.com:zyxue/rljs.git\ncd rljs\nyarn install\n```\n\n## Run server\n\n```\nyarn start\n```\n\n## Build\nThis will generate the static web site and copy it to the `docs` folder\nthat is deployed to the web site when you push to GitHub.\n\n```\nyarn build\n```\n\n## Test\n```\nyarn test\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzyxue%2Frljs","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fzyxue%2Frljs","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fzyxue%2Frljs/lists"}