{"id":46737793,"url":"https://github.com/underwit/agentsmith","last_synced_at":"2026-03-09T17:01:57.789Z","repository":{"id":230515607,"uuid":"123692749","full_name":"underwit/agentsmith","owner":"underwit","description":"Нейронная сеть оптимизируемая с помощью генетического алгоритма. Задача агента контролируемого при помощи нейронной сети состоит в том, чтобы избегать контакта с противниками, как можно более длительное время.","archived":false,"fork":false,"pushed_at":"2018-05-04T20:03:06.000Z","size":1684,"stargazers_count":8,"open_issues_count":0,"forks_count":2,"subscribers_count":2,"default_branch":"master","last_synced_at":"2024-03-30T06:46:39.601Z","etag":null,"topics":["agent","evolutionary-algorithms","evolutionary-strategy","game","genetic-algorithm","machine-learning","machine-learning-algorithms","neural-network","nn","python","python3","tkinter","unsupervised-learning"],"latest_commit_sha":null,"homepage":"","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/underwit.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}},"created_at":"2018-03-03T13:07:19.000Z","updated_at":"2024-03-30T06:46:45.095Z","dependencies_parsed_at":"2024-03-30T06:46:44.375Z","dependency_job_id":"1ac47a83-80c3-46d7-b48b-315d65d3b73e","html_url":"https://github.com/underwit/agentsmith","commit_stats":null,"previous_names":["underwit/agentsmith"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/underwit/agentsmith","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/underwit%2Fagentsmith","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/underwit%2Fagentsmith/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/underwit%2Fagentsmith/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/underwit%2Fagentsmith/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/underwit","download_url":"https://codeload.github.com/underwit/agentsmith/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/underwit%2Fagentsmith/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":30303783,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-09T14:33:48.460Z","status":"ssl_error","status_checked_at":"2026-03-09T14:33:48.027Z","response_time":61,"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":["agent","evolutionary-algorithms","evolutionary-strategy","game","genetic-algorithm","machine-learning","machine-learning-algorithms","neural-network","nn","python","python3","tkinter","unsupervised-learning"],"created_at":"2026-03-09T17:00:47.030Z","updated_at":"2026-03-09T17:01:57.773Z","avatar_url":"https://github.com/underwit.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Agent Smith\n\n### Описание\n\nНейронная сеть оптимизируемая с помощью генетического алгоритма. Задача агента контролируемого при помощи нейронной сети состоит в том, чтобы избегать контакта с противниками, как можно более длительное время.\n\n![demo](https://raw.githubusercontent.com/underwit/agentsmith/master/pics/demo.gif)\n\nПроект создан на чистом **python 3.x** без использования сторонних библиотек.\n\n**Внимание!!!**\n_прошу прощения за код, делал на скорую руку. Некоторые архитектурные решения могут покалечить психику._\n\n### Обучение\n\nДля начала обучения необходимо запустить скрипт **run.py**\n\nпример:\n```\npython run.py -s 16 32 -F 0.3  -D 0.5 -L 5000 -b 40 -r 42\n```\n\n#### Возможные опции:\n```\n-h, --help              show this help message and exit\n-s                      Форма нейронной сети \n--no-mutate             Отменить мутации новых особей\n-M {gauss,normal}       Функция мутации генов\n-F                      Доля мутируемых генов\n-D                      Отклонение при мутации\n-L                      Лимит необходимых очков\n-b                      Количество противников\n-p                      Количество особей в популяции\n-c                      Количество новых детей\n-g                      Количество поколений\n-W                      Ширина комнаты симуляции\n-H                      Высота комнаты симуляции\n-r                      Начальное состояние генератора случайных чисел\n```\n\n\n### Воспроизведение\n\nВ папке **sample** есть пара уже обученных сетей.\n\nДля просмотра работы обученной сети, необходимо воспользоваться **player.py** передав в качестве аргумента json файл с обученной сетью.\n\nПример:\n```\npython player.py sample/17-34-2_5120_30122017_1450.json\n```\n\nИз названия файла видно, что сеть имеет 17 входных нейронов 34 в скрытом слое и 2 выходных.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Funderwit%2Fagentsmith","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Funderwit%2Fagentsmith","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Funderwit%2Fagentsmith/lists"}