{"id":22268057,"url":"https://github.com/coac/commnet-bicnet","last_synced_at":"2025-07-28T12:30:51.968Z","repository":{"id":80202727,"uuid":"134057623","full_name":"Coac/CommNet-BiCnet","owner":"Coac","description":"CommNet and BiCnet implementation in tensorflow","archived":false,"fork":false,"pushed_at":"2018-07-27T11:13:25.000Z","size":68,"stargazers_count":53,"open_issues_count":3,"forks_count":17,"subscribers_count":4,"default_branch":"master","last_synced_at":"2023-10-25T21:28:52.721Z","etag":null,"topics":["multi-agent-reinforcement-learning","reinforcement-learning","tensorflow"],"latest_commit_sha":null,"homepage":null,"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/Coac.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}},"created_at":"2018-05-19T11:56:32.000Z","updated_at":"2023-06-04T17:26:26.000Z","dependencies_parsed_at":"2023-07-12T04:31:10.127Z","dependency_job_id":null,"html_url":"https://github.com/Coac/CommNet-BiCnet","commit_stats":null,"previous_names":[],"tags_count":0,"template":null,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Coac%2FCommNet-BiCnet","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Coac%2FCommNet-BiCnet/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Coac%2FCommNet-BiCnet/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Coac%2FCommNet-BiCnet/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Coac","download_url":"https://codeload.github.com/Coac/CommNet-BiCnet/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":227905533,"owners_count":17837906,"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":["multi-agent-reinforcement-learning","reinforcement-learning","tensorflow"],"created_at":"2024-12-03T11:10:31.105Z","updated_at":"2025-07-28T12:30:51.957Z","avatar_url":"https://github.com/Coac.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# CommNet-BiCnet\n[CommNet](https://arxiv.org/abs/1605.07736) and [BiCnet](https://arxiv.org/abs/1703.10069) implementation in tensorflow\n\n## Training\nTrain CommNet using DDPG algorithm\n```\npython train_comm_net.py\n```\n\n## Hypersearch\nTo find the optimal hyperparameters such as `actor_lr` or `critic_lr`, a simple grid search has been implemented. It launches multiple instances of the trainer in parallel based on the number of CPU cores.\n```\npython hypersearch.py\n```\n\n## Guessing sum environment\nIt is a simple game described in the [BiCnet](https://arxiv.org/abs/1703.10069) paper for testing if the communication works. The environment implements the crucial methods of the core gym interface from OpenAI\n\nEach agent receives a scalar sampled between `[−10, 10]` under a truncated Gaussian. Each agent needs to output the sum of all inputs received among the agents. An agent gets a normalized reward between `[0, 1]` based on the absolute difference between the sum and its output.\n\n## Results\n### Training CommNet in the Guessing sum env with 2 agents\n![2_agents_commnet_training_reward](docs/2_agents_commnet.png)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcoac%2Fcommnet-bicnet","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcoac%2Fcommnet-bicnet","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcoac%2Fcommnet-bicnet/lists"}