{"id":16316969,"url":"https://github.com/sonnhfit/deepair","last_synced_at":"2025-03-22T21:31:33.993Z","repository":{"id":36993428,"uuid":"498064033","full_name":"sonnhfit/deepair","owner":"sonnhfit","description":"PyTorch implementations of Deep reinforcement learning algorithms.","archived":false,"fork":false,"pushed_at":"2022-07-29T07:25:51.000Z","size":685,"stargazers_count":5,"open_issues_count":3,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-18T14:53:42.928Z","etag":null,"topics":["deep-reinforcement-learning","dqn-pytorch","rainbow","reinforcement-learning"],"latest_commit_sha":null,"homepage":"https://deepair.readthedocs.io","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/sonnhfit.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}},"created_at":"2022-05-30T18:56:52.000Z","updated_at":"2023-06-16T06:07:57.000Z","dependencies_parsed_at":"2022-06-29T10:29:42.338Z","dependency_job_id":null,"html_url":"https://github.com/sonnhfit/deepair","commit_stats":null,"previous_names":[],"tags_count":4,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sonnhfit%2Fdeepair","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sonnhfit%2Fdeepair/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sonnhfit%2Fdeepair/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sonnhfit%2Fdeepair/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/sonnhfit","download_url":"https://codeload.github.com/sonnhfit/deepair/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245022533,"owners_count":20548552,"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","dqn-pytorch","rainbow","reinforcement-learning"],"created_at":"2024-10-10T22:06:15.252Z","updated_at":"2025-03-22T21:31:33.581Z","avatar_url":"https://github.com/sonnhfit.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Deepair is a Deep Reinforcement Learning library\n\n[![PyPI version](https://badge.fury.io/py/deepair.svg)](https://badge.fury.io/py/deepair)\n[![Documentation Status](https://readthedocs.org/projects/deepair/badge/?version=latest)](https://deepair.readthedocs.io/en/latest/?badge=latest)\n\nDeepair implementations of reinforcement learning algorithms. It focus on DRL algorithms and implementing the latest advancements in DRL. Highly customizable support for training processes. Suitable for the research and application of the latest technologies in reinforcement learning.\n\n\n\n# Features\n\n# Documentation\nDocumentation is available: [https://deepair.readthedocs.io/](https://deepair.readthedocs.io/)\n\n# Installation\n\n```\npip install deepair\n```\n\nor\n```\npip install git+https://github.com/sonnhfit/deepair.git\n```\n\n# Example\n\n```python\nimport gym\nfrom deepair.dqn import Rainbow\n\nenv = gym.make('LunarLander-v2')\n\nrain = Rainbow(env=env, memory_size=10000, batch_size=32, target_update=256)\n\nrain.train(timesteps=200000)\n\n# test\nstate = env.reset()\ndone = False\nscore = 0\n\nwhile not done:\n    action = rain.select_action(state, deterministic=True)\n    next_state, reward, done, info = env.step(action)\n\n    state = next_state\n    score += reward\n\nprint(\"score: \", score)\n```\n\n![rainbow lunalander env](docs/source/_static/img/rainbow_lunalander.gif)\n\n# Implemented Algorithms\n\n# Tutorial\n- save model \n- load model\n\n# How To Contribute\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsonnhfit%2Fdeepair","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsonnhfit%2Fdeepair","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsonnhfit%2Fdeepair/lists"}