{"id":24554068,"url":"https://github.com/andrewimpellitteri/floor-cleaner-agent","last_synced_at":"2026-05-21T10:02:20.485Z","repository":{"id":273130646,"uuid":"918787680","full_name":"andrewimpellitteri/floor-cleaner-agent","owner":"andrewimpellitteri","description":"An RL agent that finds an optimal policy of cleaning dirt off a floor with a power washer.","archived":false,"fork":false,"pushed_at":"2025-02-13T22:04:09.000Z","size":29611,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-23T15:59:25.034Z","etag":null,"topics":["bd3","cfd","fluid-dynamics","fluid-simulation","ppo-agent","reinforcement-learning","reinforcement-learning-environments","rl"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/andrewimpellitteri.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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":"2025-01-18T21:15:00.000Z","updated_at":"2025-02-13T22:04:12.000Z","dependencies_parsed_at":"2025-03-16T15:15:28.139Z","dependency_job_id":"a908157b-cafb-4560-8248-5700dc60eefa","html_url":"https://github.com/andrewimpellitteri/floor-cleaner-agent","commit_stats":null,"previous_names":["andrewimpellitteri/floor-cleaner-agent"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/andrewimpellitteri/floor-cleaner-agent","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/andrewimpellitteri%2Ffloor-cleaner-agent","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/andrewimpellitteri%2Ffloor-cleaner-agent/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/andrewimpellitteri%2Ffloor-cleaner-agent/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/andrewimpellitteri%2Ffloor-cleaner-agent/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/andrewimpellitteri","download_url":"https://codeload.github.com/andrewimpellitteri/floor-cleaner-agent/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/andrewimpellitteri%2Ffloor-cleaner-agent/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":33297118,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-21T02:57:32.698Z","status":"ssl_error","status_checked_at":"2026-05-21T02:57:31.990Z","response_time":62,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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":["bd3","cfd","fluid-dynamics","fluid-simulation","ppo-agent","reinforcement-learning","reinforcement-learning-environments","rl"],"created_at":"2025-01-23T02:17:17.200Z","updated_at":"2026-05-21T10:02:20.450Z","avatar_url":"https://github.com/andrewimpellitteri.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Cleaning Room RL Agent\n\nThis project builds a Reinforcement Learning (RL) agent to find an optimal floor cleaning method using a power washer in a simulated environment. The agent can move, rotate, and spray the washer to clean dirt, with the reward being the inverse of dirt concentration on the floor.\n\n## Features\n\n- **Power Washer Simulation**: Agent can move and rotate to spray dirt.\n- **RL Training**: Trains an agent using Proximal Policy Optimization (PPO).\n- **Custom Environment**: Built with `gymnasium` for easy integration with RL algorithms.\n\n## Dependencies\n\nInstall required packages:\n\n```bash\npip install stable-baselines3 torch numpy gymnasium matplotlib\n```\n## Setup and Usage\n1. **Training the Agent**\nRun the train_agent() function to train the PPO agent:\n\npython train_agent.py\nThis trains the agent with 4 parallel environments for 1,000,000 timesteps, saving the model as cleaning_agent_final.\n\n2. **Evaluating the Agent**\nAfter training, evaluate the agent's performance:\n\n```bash\npython evaluate_agent.py\n```\n\nThis runs 10 evaluation episodes and prints the average reward.\n\nFeel free to fork and submit pull requests for improvements.\n\n## License\nThis project is licensed under the MIT License.\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fandrewimpellitteri%2Ffloor-cleaner-agent","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fandrewimpellitteri%2Ffloor-cleaner-agent","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fandrewimpellitteri%2Ffloor-cleaner-agent/lists"}