{"id":19736016,"url":"https://github.com/ikostrikov/pytorch-trpo","last_synced_at":"2025-04-06T10:13:29.085Z","repository":{"id":85543743,"uuid":"92508884","full_name":"ikostrikov/pytorch-trpo","owner":"ikostrikov","description":"PyTorch implementation of Trust Region Policy Optimization","archived":false,"fork":false,"pushed_at":"2018-09-13T13:59:57.000Z","size":10,"stargazers_count":439,"open_issues_count":7,"forks_count":90,"subscribers_count":11,"default_branch":"master","last_synced_at":"2025-03-30T09:07:56.589Z","etag":null,"topics":["continuous-control","deep-learning","deep-reinforcement-learning","mujoco","pytorch","reinforcement-learning","trpo","trust-region-policy-optimization"],"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/ikostrikov.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.md","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":"2017-05-26T12:33:18.000Z","updated_at":"2025-03-25T12:11:05.000Z","dependencies_parsed_at":"2023-03-02T14:45:40.757Z","dependency_job_id":null,"html_url":"https://github.com/ikostrikov/pytorch-trpo","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/ikostrikov%2Fpytorch-trpo","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ikostrikov%2Fpytorch-trpo/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ikostrikov%2Fpytorch-trpo/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ikostrikov%2Fpytorch-trpo/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ikostrikov","download_url":"https://codeload.github.com/ikostrikov/pytorch-trpo/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247464223,"owners_count":20942970,"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":["continuous-control","deep-learning","deep-reinforcement-learning","mujoco","pytorch","reinforcement-learning","trpo","trust-region-policy-optimization"],"created_at":"2024-11-12T01:04:45.935Z","updated_at":"2025-04-06T10:13:29.062Z","avatar_url":"https://github.com/ikostrikov.png","language":"Python","funding_links":[],"categories":["Paper implementations｜论文实现","Paper implementations"],"sub_categories":["Other libraries｜其他库:","Other libraries:"],"readme":"# PyTorch implementation of TRPO\n\nTry my implementation of [PPO](github.com/ikostrikov/pytorch-a2c-ppo-acktr/) (aka newer better variant of TRPO), unless you need to you TRPO for some specific reasons.\n\n##\n\nThis is a PyTorch implementation of [\"Trust Region Policy Optimization (TRPO)\"](https://arxiv.org/abs/1502.05477).\n\nThis is code mostly ported from [original implementation by John Schulman](https://github.com/joschu/modular_rl). In contrast to [another implementation of TRPO in PyTorch](https://github.com/mjacar/pytorch-trpo), this implementation uses exact Hessian-vector product instead of finite differences approximation.\n\n## Contributions\n\nContributions are very welcome. If you know how to make this code better, don't hesitate to send a pull request.\n\n## Usage\n\n```\npython main.py --env-name \"Reacher-v1\"\n```\n\n## Recommended hyper parameters\n\nInvertedPendulum-v1: 5000\n\nReacher-v1, InvertedDoublePendulum-v1: 15000\n\nHalfCheetah-v1, Hopper-v1, Swimmer-v1, Walker2d-v1: 25000\n\nAnt-v1, Humanoid-v1: 50000\n\n## Results\n\nMore or less similar to the original code. Coming soon.\n\n## Todo\n\n- [ ] Plots.\n- [ ] Collect data in multiple threads.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fikostrikov%2Fpytorch-trpo","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fikostrikov%2Fpytorch-trpo","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fikostrikov%2Fpytorch-trpo/lists"}