{"id":21901312,"url":"https://github.com/themcaffee/road-rage","last_synced_at":"2026-04-19T07:34:08.694Z","repository":{"id":39740455,"uuid":"147984685","full_name":"themcaffee/road-rage","owner":"themcaffee","description":"Use deep learning to set red light timings to optimize throughput","archived":false,"fork":false,"pushed_at":"2023-02-15T21:32:12.000Z","size":87,"stargazers_count":1,"open_issues_count":3,"forks_count":0,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-07-05T05:38:49.142Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","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/themcaffee.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":"2018-09-09T01:54:55.000Z","updated_at":"2022-08-30T02:58:33.000Z","dependencies_parsed_at":"2025-01-27T06:43:28.482Z","dependency_job_id":"61893aaf-cb82-46c1-9517-25d8f42730f9","html_url":"https://github.com/themcaffee/road-rage","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/themcaffee/road-rage","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/themcaffee%2Froad-rage","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/themcaffee%2Froad-rage/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/themcaffee%2Froad-rage/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/themcaffee%2Froad-rage/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/themcaffee","download_url":"https://codeload.github.com/themcaffee/road-rage/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/themcaffee%2Froad-rage/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31999002,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-18T20:23:30.271Z","status":"online","status_checked_at":"2026-04-19T02:00:07.110Z","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":[],"created_at":"2024-11-28T15:13:01.106Z","updated_at":"2026-04-19T07:34:08.662Z","avatar_url":"https://github.com/themcaffee.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Road Rage\n\nHate traffic? Me too. Traffic lights should be smarter and controlling\nthem is a juicy optimization problem. This experiment uses reinforcement\nlearning to dynamically control stop lights to optimize getting people\nwhere they want to go.\n\n\n## Usage\n\n\n```\n# Install sumo the traffic simulator\nsudo apt-get install sumo sumo-tools sumo-doc\nexport $SUMO_HOME=/usr/share/sumo\n\n# Setup and install requirements\npython3 -m virtualenv venv\nsource venv/bin/activate\npip install -r requirements.txt\n\n# Run training and evaluation\npython run.py\n```\n\n\n## Options\n\n```\npython run.py --help\n\nUsage: run.py [options]\n\nOptions:\n  -h, --help            show this help message and exit\n  --gui                 Run the GUI version of sumo\n  --type=TYPE           The type of prediction to use\n  --training-steps=TRAINING_STEPS\n                        The number of simulation steps to train for\n  --training-max-steps=TRAINING_MAX_STEPS\n                        The maximum number of steps during training per\n                        episode\n  --training-warmup=TRAINING_WARMUP\n                        Steps to take randomly before prediction\n  --eval-episodes=EVAL_EPISODES\n                        Number of episodes to evaluate for\n  --eval-max-steps=EVAL_MAX_STEPS\n                        Max simulation steps per episode during training\n```\n\n\n## Results\n\nReward (higher is better):\n\n- DQN (trained 200000 epochs): 13027\n- random: 6965\n- timed: 1495","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fthemcaffee%2Froad-rage","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fthemcaffee%2Froad-rage","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fthemcaffee%2Froad-rage/lists"}