{"id":31684522,"url":"https://github.com/simplisoni/3d-reinforcementlearning-simulator","last_synced_at":"2026-04-19T06:37:32.365Z","repository":{"id":316621650,"uuid":"1064155267","full_name":"SimpliSoni/3D-ReinforcementLearning-Simulator","owner":"SimpliSoni","description":"An interactive, web-based simulator for visualizing reinforcement learning policies in 3D environments","archived":false,"fork":false,"pushed_at":"2025-09-25T16:54:09.000Z","size":102,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-09-25T18:12:25.475Z","etag":null,"topics":["3d","reinforcement-learning","simulation","three-js"],"latest_commit_sha":null,"homepage":"https://3-d-reinforcement-learning-simulato.vercel.app","language":"TypeScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/SimpliSoni.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,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-09-25T16:09:02.000Z","updated_at":"2025-09-25T16:54:12.000Z","dependencies_parsed_at":"2025-09-25T18:12:27.558Z","dependency_job_id":"ad454ce0-1e40-4bc7-a4cb-8747dcbab6ae","html_url":"https://github.com/SimpliSoni/3D-ReinforcementLearning-Simulator","commit_stats":null,"previous_names":["simplisoni/3d-reinforcementlearning-simulator"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/SimpliSoni/3D-ReinforcementLearning-Simulator","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SimpliSoni%2F3D-ReinforcementLearning-Simulator","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SimpliSoni%2F3D-ReinforcementLearning-Simulator/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SimpliSoni%2F3D-ReinforcementLearning-Simulator/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SimpliSoni%2F3D-ReinforcementLearning-Simulator/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/SimpliSoni","download_url":"https://codeload.github.com/SimpliSoni/3D-ReinforcementLearning-Simulator/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/SimpliSoni%2F3D-ReinforcementLearning-Simulator/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":278909744,"owners_count":26066897,"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":"2025-10-08T02:00:06.501Z","response_time":56,"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":["3d","reinforcement-learning","simulation","three-js"],"created_at":"2025-10-08T08:09:27.395Z","updated_at":"2025-10-08T08:11:22.453Z","avatar_url":"https://github.com/SimpliSoni.png","language":"TypeScript","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 3D-ReinforcementLearning-Simulator\n\nAn interactive, web-based simulator for visualizing reinforcement learning policies in 3D environments\n\n\u003cimg width=\"1336\" height=\"650\" alt=\"image\" src=\"https://github.com/user-attachments/assets/0595c460-1b49-4a7a-bec5-de1ca0044d77\" /\u003e\n\n\n-----\n\n  * **Render 3D Environments**: Load and display different simulation environments, like a Grid World.\n  * **Upload and Test Policies**: Users can upload pre-trained policy files (e.g., a Q-table in JSON format) to guide the agent.\n  * **Control the Simulation**: Play, pause, step through, and reset the agent's interaction with the environment.\n  * **Visualize Key Metrics**: Toggle visual aids like Q-values to better understand the agent's decision-making process at each step.\n\nThis tool is invaluable for students, researchers, and developers who need to bridge the gap between RL theory and practical application.\n\n-----\n\n## Built With\n\n  * React\n  * Three.js\n\n-----\n\n## Getting Started\n\nTo get a local copy up and running, follow these simple steps.\n\n### Prerequisites\n\nYou'll need Node.js and npm installed on your machine.\n\n```bash\nnpm install npm@latest -g\n```\n\n### Installation\n\n1.  Clone the repository:\n    ```bash\n    git clone https://github.com/SimpliSoni/3D-ReinforcementLearning-Simulator.git\n    ```\n2.  Navigate to the project directory:\n    ```bash\n    cd 3D-ReinforcementLearning-Simulator\n    ```\n3.  Install NPM packages:\n    ```bash\n    npm install\n    ```\n4.  Start the development server:\n    ```bash\n    npm start\n    ```\n\nYour browser should automatically open to `http://localhost:3000`.\n\n-----\n\n## Usage\n\nOnce the application is running, you can interact with the simulation using the control panel:\n\n1.  **Select an Environment**: Use the dropdown menu to choose a simulation world (e.g., \"Grid World\").\n2.  **Upload a Policy**: Click \"**Choose File**\" to upload a compatible policy file (e.g., a JSON file containing a Q-table).\n3.  **Run the Simulation**: Use the \"**Play**,\" \"**Pause**,\" and \"**Step**\" buttons to observe the agent's behavior.\n4.  **Analyze**: Toggle the \"**Show Q-Values**\" checkbox to visualize the agent's learned values for different actions in its current state.\n\nThis allows for a direct and intuitive analysis of how the trained policy performs in a 3D space.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsimplisoni%2F3d-reinforcementlearning-simulator","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsimplisoni%2F3d-reinforcementlearning-simulator","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsimplisoni%2F3d-reinforcementlearning-simulator/lists"}