{"id":22553713,"url":"https://github.com/kornbergfresnel/commnet","last_synced_at":"2025-08-23T00:18:09.683Z","repository":{"id":68596534,"uuid":"109588229","full_name":"KornbergFresnel/CommNet","owner":"KornbergFresnel","description":"an implementation of CommNet","archived":false,"fork":false,"pushed_at":"2017-11-14T11:58:12.000Z","size":321,"stargazers_count":31,"open_issues_count":0,"forks_count":3,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-03-24T05:43:27.176Z","etag":null,"topics":["deep-reinforcement-learning","multiagent","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/KornbergFresnel.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":"2017-11-05T14:49:57.000Z","updated_at":"2024-12-02T11:58:04.000Z","dependencies_parsed_at":"2023-02-21T06:45:54.544Z","dependency_job_id":null,"html_url":"https://github.com/KornbergFresnel/CommNet","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/KornbergFresnel%2FCommNet","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/KornbergFresnel%2FCommNet/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/KornbergFresnel%2FCommNet/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/KornbergFresnel%2FCommNet/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/KornbergFresnel","download_url":"https://codeload.github.com/KornbergFresnel/CommNet/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248155619,"owners_count":21056671,"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","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":["deep-reinforcement-learning","multiagent","reinforcement-learning"],"created_at":"2024-12-07T18:10:58.783Z","updated_at":"2025-04-10T04:22:59.250Z","avatar_url":"https://github.com/KornbergFresnel.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# CommNet\nan implementation of CommNet, arxiv link: [Learning Multiagent Communication with Backpropagation](http://arxiv.org/abs/1605.07736)\n\n**What's CommNet**\n\nMany tasks in AI require the collaboration of multiple agents. Typically, the communication protocol between agents is manually specified and not altered during training. *CommNet* is a simple neural model, that uses continuous communication for fully cooperative tasks. The model consists of multiple agents and the communication between them is learned alongside their policy. \n\n*Demonstrating*\n\ndemonstrating the ability of the agents to learn to communicate amongst themselves, yielding improved performance over non-communicative agents and baselines. In some cases, it is possible to interpret the language devised by the agents, revealing simple but effective strategies for solving the task at hand.\n\n*Structure*\n\n\u003cimg src=\"./assets/commnet_model.png\" width=\"70%\" /\u003e\n\n*Tasks*\n\n1. Leaver Pulling game\n2. Traffic Junction\n\n**Plot of Loss (leaver pulling game)**\n\n\u003cimg src=\"./assets/loss.png\" width=\"70%\" /\u003e\n\n**Plot of reward and baseline**\n\n\u003cimg src=\"./assets/reward.png\" width=\"70%\"/\u003e\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkornbergfresnel%2Fcommnet","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fkornbergfresnel%2Fcommnet","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkornbergfresnel%2Fcommnet/lists"}