{"id":31815587,"url":"https://github.com/mvrahden/learning-agents","last_synced_at":"2025-10-11T09:18:21.069Z","repository":{"id":31369445,"uuid":"126791849","full_name":"mvrahden/learning-agents","owner":"mvrahden","description":"Reinforcement Learning Agents learn with Deep-Q-Learning Network to collect superior and avoid inferior items.","archived":false,"fork":false,"pushed_at":"2023-02-27T21:41:32.000Z","size":6389,"stargazers_count":2,"open_issues_count":10,"forks_count":1,"subscribers_count":2,"default_branch":"master","last_synced_at":"2023-03-01T16:26:20.126Z","etag":null,"topics":["agent","ai","angular","artificial-intelligence","artificial-neural-networks","deep-learning","deep-q-learning","deep-q-network","deep-reinforcement-learning","deepmind","dqn","learning-agents","material","nodejs","q-learning","sarsa","simulation"],"latest_commit_sha":null,"homepage":"https://mvrahden.github.io/learning-agents/","language":"HTML","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/mvrahden.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":"2018-03-26T07:41:06.000Z","updated_at":"2023-03-01T16:26:20.127Z","dependencies_parsed_at":"2022-09-18T12:32:13.335Z","dependency_job_id":null,"html_url":"https://github.com/mvrahden/learning-agents","commit_stats":null,"previous_names":[],"tags_count":null,"template":null,"template_full_name":null,"purl":"pkg:github/mvrahden/learning-agents","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mvrahden%2Flearning-agents","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mvrahden%2Flearning-agents/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mvrahden%2Flearning-agents/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mvrahden%2Flearning-agents/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/mvrahden","download_url":"https://codeload.github.com/mvrahden/learning-agents/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/mvrahden%2Flearning-agents/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":279006751,"owners_count":26084177,"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":"2025-10-11T02:00:06.511Z","response_time":55,"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":["agent","ai","angular","artificial-intelligence","artificial-neural-networks","deep-learning","deep-q-learning","deep-q-network","deep-reinforcement-learning","deepmind","dqn","learning-agents","material","nodejs","q-learning","sarsa","simulation"],"created_at":"2025-10-11T09:18:17.296Z","updated_at":"2025-10-11T09:18:21.060Z","avatar_url":"https://github.com/mvrahden.png","language":"HTML","readme":"# Learning Agents\n\nThe content of this repository can be viewed on its [GitHub page](https://mvrahden.github.io/learning-agents).\nIt is shown an environment which is an extended version of the \"Waterworld\" example of the Stanford University CS group - more specific by Andrej Karpathy.\nYou'll find multiple pages, each with different content.\n\n- **Pre-Trained**: This page shows two agents which were trained in a simulation run.\n- **Simulation**: The simulation environment offers the ability to run individual simulations.\n- **Explanation**: This page offers explanatory content regarding the logics and technical background of the simulation.\n- **DQN-Method**: This page offers even more insight into how the agents inference mechanism, namely the DQN-Method, is implemented.\n- **About**: This page offers an overview of the Dependencies of this project.\n\nThe content of this Website is for educational purposes only.\n\n## Overview of the System as UML\n\nPlease see the section [Dependencies](#dependencies) for the displayed modules. \n\n\u003cimg src=\"src/assets/project-uml.svg\" alt=\"UML Diagram\" width=\"420\"/\u003e\n\n## Local Installation\n\nTo run the code on a local machine please follow the listed steps:\n\n### Pre-Setup\n\n1. Install NodeJS, NPM (ships with NodeJS) \u0026 git (if not done yet)  \n  Please follow the steps on their respective website [node, npm](https://www.nodejs.org) \u0026 [git](https://git-scm.com/) or in any given Web-Tutorial\n2. Install Typescript \u0026 Angular CLI as global dependencies  \n  Please follow the following steps in your command line (or the steps on their respective websites)\n\n```\nnpm install -g typescript @angular/cli\n```\n\n### Actual Installation\n\n3. In your command line change into a target directory and clone the code via `git` into this directory\n\n```\ngit clone https://github.com/mvrahden/learning-agents.git\n```\n\n4. Change into the newly created directory `cd learning-agents`\n5. Install all project related dependencies via `npm install`\n6. Run the code via the Angular CLI `ng serve --open`  \n  This should open a new tab in your configured web browser\n\n### Update the GitHub Page\n\n1. build the current code base:\n```\nng build --prod --output-path=docs --base-href \"https://mvrahden.github.io/learning-agents/\"\n```\n2. restore the `404.html` file. \n3. `git commit` and `git push`\n\n## Dependencies\n\n1. [Learning Agents](https://github.com/mvrahden/learning-agents): Implementation of the Simulation Flow Control and the Frontend View\n2. [Learning Agents Model](https://github.com/mvrahden/learning-agents-model): Implementation of the Entities involved in the Simulation\n3. [reinforce-js](https://github.com/mvrahden/reinforce-js): Implementation of the DQN-Solver (also available via [NPM](https://www.npmjs.com/package/reinforce-js))\n4. [recurrent-js](https://github.com/mvrahden/recurrent-js): Implementation of neural networks graph model and matrix operations (also available via [NPM](https://www.npmjs.com/package/recurrent-js))\n5. [Angular](https://angular.io): Mobile \u0026 Desktop Frontend Framework\n6. [Angular Material](https://material.angular.io): Material Design Components for the Angular Frontend Framework\n\n## License\n\nAs of License-File: [MIT](LICENSE)","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmvrahden%2Flearning-agents","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmvrahden%2Flearning-agents","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmvrahden%2Flearning-agents/lists"}