{"id":13564703,"url":"https://github.com/seungeunrho/minimalRL","last_synced_at":"2025-04-03T21:31:25.231Z","repository":{"id":38392090,"uuid":"182995939","full_name":"seungeunrho/minimalRL","owner":"seungeunrho","description":"Implementations of basic RL algorithms with minimal lines of codes! (pytorch based)","archived":false,"fork":false,"pushed_at":"2023-04-22T09:06:41.000Z","size":62,"stargazers_count":2993,"open_issues_count":22,"forks_count":463,"subscribers_count":50,"default_branch":"master","last_synced_at":"2025-03-30T23:06:13.613Z","etag":null,"topics":["a2c","a3c","acer","ddpg","deep-learning","deep-reinforcement-learning","dqn","machine-learning","policy-gradients","ppo","pytorch","reinforce","reinforcement-learning","sac","simple"],"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/seungeunrho.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,"publiccode":null,"codemeta":null}},"created_at":"2019-04-23T10:57:44.000Z","updated_at":"2025-03-30T19:05:48.000Z","dependencies_parsed_at":"2024-08-01T13:20:54.123Z","dependency_job_id":"c9878dfe-b8bf-4643-b359-f0b319113c53","html_url":"https://github.com/seungeunrho/minimalRL","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/seungeunrho%2FminimalRL","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/seungeunrho%2FminimalRL/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/seungeunrho%2FminimalRL/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/seungeunrho%2FminimalRL/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/seungeunrho","download_url":"https://codeload.github.com/seungeunrho/minimalRL/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247083321,"owners_count":20880809,"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":["a2c","a3c","acer","ddpg","deep-learning","deep-reinforcement-learning","dqn","machine-learning","policy-gradients","ppo","pytorch","reinforce","reinforcement-learning","sac","simple"],"created_at":"2024-08-01T13:01:34.662Z","updated_at":"2025-04-03T21:31:24.892Z","avatar_url":"https://github.com/seungeunrho.png","language":"Python","funding_links":[],"categories":["Python","时间序列"],"sub_categories":["网络服务_其他"],"readme":"# minimalRL-pytorch\n\nImplementations of basic RL algorithms with minimal lines of codes! (PyTorch based)\n\n* Each algorithm is complete within a single file.\n\n* Length of each file is up to 100~150 lines of codes.\n\n* Every algorithm can be trained within 30 seconds, even without GPU.\n\n* Envs are fixed to \"CartPole-v1\". You can just focus on the implementations.\n\n\n\n## Algorithms\n1. [REINFORCE](https://github.com/seungeunrho/minimalRL/blob/master/REINFORCE.py) (67 lines)\n2. [Vanilla Actor-Critic](https://github.com/seungeunrho/minimalRL/blob/master/actor_critic.py) (98 lines)\n3. [DQN](https://github.com/seungeunrho/minimalRL/blob/master/dqn.py) (112 lines,  including replay memory and target network)\n4. [PPO](https://github.com/seungeunrho/minimalRL/blob/master/ppo.py) (119 lines,  including GAE)\n5. [DDPG](https://github.com/seungeunrho/minimalRL/blob/master/ddpg.py) (145 lines, including OU noise and soft target update)\n6. [A3C](https://github.com/seungeunrho/minimalRL/blob/master/a3c.py) (129 lines)\n7. [ACER](https://github.com/seungeunrho/minimalRL/blob/master/acer.py) (149 lines)\n8. [A2C](https://github.com/seungeunrho/minimalRL/blob/master/a2c.py) (188 lines)\n9. [SAC](https://github.com/seungeunrho/minimalRL/blob/master/sac.py) (171 lines) added!! \n10. [PPO-Continuous](https://github.com/seungeunrho/minimalRL/blob/master/ppo-continuous.py) (161 lines) added!!\n11. [Vtrace](https://github.com/seungeunrho/minimalRL/blob/master/vtrace.py) (137 lines) added!!\n12. Any suggestion ...? \n\n\n## Dependencies\n1. PyTorch\n2. OpenAI GYM ( \u003e 0.26.2 IMPORTANT!! No longer support for the previous versions)\n\n## Usage\n```bash\n# Works only with Python 3.\n# e.g.\npython3 REINFORCE.py\npython3 actor_critic.py\npython3 dqn.py\npython3 ppo.py\npython3 ddpg.py\npython3 a3c.py\npython3 a2c.py\npython3 acer.py\npython3 sac.py\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fseungeunrho%2FminimalRL","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fseungeunrho%2FminimalRL","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fseungeunrho%2FminimalRL/lists"}