{"id":24241847,"url":"https://github.com/sophiaas/rlbase","last_synced_at":"2026-05-14T21:35:21.196Z","repository":{"id":40979769,"uuid":"197673709","full_name":"sophiaas/rlbase","owner":"sophiaas","description":"Modular Deep RL infrastructure in PyTorch","archived":false,"fork":false,"pushed_at":"2024-07-25T10:59:54.000Z","size":2408,"stargazers_count":3,"open_issues_count":2,"forks_count":0,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-10-09T15:43:52.130Z","etag":null,"topics":["a2c","deep-reinforcement-learning","hierarchical-reinforcement-learning","option-critic","policy-gradient","ppo","proximal-policy-optimization","pytorch-rl","reinforcement-learning"],"latest_commit_sha":null,"homepage":"","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/sophiaas.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,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2019-07-19T00:20:26.000Z","updated_at":"2025-03-09T10:47:03.000Z","dependencies_parsed_at":"2025-03-04T15:42:06.961Z","dependency_job_id":null,"html_url":"https://github.com/sophiaas/rlbase","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/sophiaas/rlbase","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sophiaas%2Frlbase","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sophiaas%2Frlbase/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sophiaas%2Frlbase/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sophiaas%2Frlbase/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/sophiaas","download_url":"https://codeload.github.com/sophiaas/rlbase/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/sophiaas%2Frlbase/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":33044244,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-13T13:14:54.681Z","status":"online","status_checked_at":"2026-05-14T02:00:06.663Z","response_time":57,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"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":["a2c","deep-reinforcement-learning","hierarchical-reinforcement-learning","option-critic","policy-gradient","ppo","proximal-policy-optimization","pytorch-rl","reinforcement-learning"],"created_at":"2025-01-14T21:50:14.927Z","updated_at":"2026-05-14T21:35:21.191Z","avatar_url":"https://github.com/sophiaas.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# rlbase\n\nModular Deep RL infrastructure in PyTorch.\n\nCurrently implemented algorithms include PPO and PPOC (Option-Critic trained with Proximal Policy Optimization).\n\nTo train, first write a config file and save to `configs/ppo` or `configs/ppoc.` A config file specifies parameters in config objects (found in `core/config.py`) for each component of the model and experiment, such as optimization hyperparameters, network architectures, environments, logging behavior, etc. See example config at `configs/ppo/lightbot.py`\n\nThe specified configuration and algorithm can then be run by calling:\n\n`python train.py --config [config file name] --algo [ppo or ppoc]`\n\nSee `train.py` for other options.\n\nTo evaluate a pre-trained model, run:\n\n`python evaluate.py --model_dir [logging directory] --episode [episode to load checkpoint from] --n_eval_steps [number of steps to evaluate]`\n\nData from the evaluated model is saved to `[logging directory]/evaluate/`\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsophiaas%2Frlbase","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsophiaas%2Frlbase","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsophiaas%2Frlbase/lists"}