{"id":20449675,"url":"https://github.com/emmanuelmess/simplifiedrimworldrl","last_synced_at":"2026-05-18T09:33:41.278Z","repository":{"id":92103912,"uuid":"313093745","full_name":"EmmanuelMess/SimplifiedRimWorldRL","owner":"EmmanuelMess","description":"Very simple implementation of RimWorld's mechanics in a gym env to train a reinforcement learning algorithm","archived":false,"fork":false,"pushed_at":"2020-11-19T23:08:52.000Z","size":71,"stargazers_count":3,"open_issues_count":0,"forks_count":2,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-08-31T22:35:59.601Z","etag":null,"topics":["gym-environment","reinforcement-learning"],"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/EmmanuelMess.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":"2020-11-15T18:13:20.000Z","updated_at":"2025-04-28T12:35:26.000Z","dependencies_parsed_at":"2023-04-25T16:32:20.469Z","dependency_job_id":null,"html_url":"https://github.com/EmmanuelMess/SimplifiedRimWorldRL","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/EmmanuelMess/SimplifiedRimWorldRL","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EmmanuelMess%2FSimplifiedRimWorldRL","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EmmanuelMess%2FSimplifiedRimWorldRL/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EmmanuelMess%2FSimplifiedRimWorldRL/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EmmanuelMess%2FSimplifiedRimWorldRL/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/EmmanuelMess","download_url":"https://codeload.github.com/EmmanuelMess/SimplifiedRimWorldRL/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EmmanuelMess%2FSimplifiedRimWorldRL/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":33172612,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-18T09:27:30.708Z","status":"ssl_error","status_checked_at":"2026-05-18T09:27:28.300Z","response_time":71,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: 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":["gym-environment","reinforcement-learning"],"created_at":"2024-11-15T10:43:33.420Z","updated_at":"2026-05-18T09:33:41.262Z","avatar_url":"https://github.com/EmmanuelMess.png","language":"Python","funding_links":["https://www.patreon.com/emmanuelmess"],"categories":[],"sub_categories":[],"readme":"# Simplified RimWorld Env for RL\n\nVery simple implementation of RimWorld's mechanics in a gym env to train a reinforcement learning algorithm\n\n* A single deep Q learning algo learns how to kill enemies\n* The friends are allowed instant movement on a 10 by 10 grid\n* New enemy wave is spawned each time the last one is fully killed\n* At the start waves are 1 enemy, at the half mark it goes to 2\n* At the start the AI controls 1 actor, at the half mark it goes to 2\n* Shots are instants\n* There is a single box that provides cover\n\nRewards:\n* 1 per kill\n* -1 per actor that is killed\n* -0.0000002 for moving to an occupied spot\n* -0.0000002 for shooting an empty spot\n* -0.05 for not doing anything for 10 consecutive steps\n* +0.5 for killing all enemies in a round\n\n[![Chat on Telegram](https://img.shields.io/badge/Chat%20on-Telegram-brightgreen.svg)](https://t.me/EmmanuelsApps)  \n\n## Graph\n\u003cimg src=\"plot.png\" width=\"640\"/\u003e\nThe half point decrease in scores is because the amount of initial enemies and actors are upped.\n\nThanks:\n* [seungeunrho/minimalRL](https://github.com/seungeunrho/minimalRL)\n* [Learning to be a Bot: Reinforcement Learning in Shooter Games (Michelle McPartland and Marcus Gallagher, 2008)](https://www.aaai.org/Papers/AIIDE/2008/AIIDE08-013.pdf)\n----\n\u003ca class=\"imgpatreon\" href=\"https://www.patreon.com/emmanuelmess\" target=\"_blank\"\u003e\n\u003cimg alt=\"Become a patreon\" src=\"https://user-images.githubusercontent.com/10991116/56376378-07065400-61de-11e9-9583-8ff2148aa41c.png\" width=150px\u003e\u003c/a\u003e","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Femmanuelmess%2Fsimplifiedrimworldrl","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Femmanuelmess%2Fsimplifiedrimworldrl","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Femmanuelmess%2Fsimplifiedrimworldrl/lists"}