{"id":22919766,"url":"https://github.com/stanfordasl/barc","last_synced_at":"2025-05-12T20:19:34.860Z","repository":{"id":81489640,"uuid":"137541933","full_name":"StanfordASL/BaRC","owner":"StanfordASL","description":"Contains the code for \"BaRC: Backward Reachability Curriculum for Robotic Reinforcement Learning\" by Boris Ivanovic, James Harrison, Apoorva Sharma, Mo Chen, Marco Pavone.","archived":false,"fork":false,"pushed_at":"2018-06-20T21:11:28.000Z","size":221,"stargazers_count":12,"open_issues_count":0,"forks_count":7,"subscribers_count":7,"default_branch":"master","last_synced_at":"2025-04-01T03:02:06.863Z","etag":null,"topics":["curriculum-learning","dynamical-systems","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":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/StanfordASL.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":"2018-06-16T00:19:46.000Z","updated_at":"2023-06-02T12:49:36.000Z","dependencies_parsed_at":null,"dependency_job_id":"1de71f81-cb4f-44db-a5ec-486985da36c5","html_url":"https://github.com/StanfordASL/BaRC","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/StanfordASL%2FBaRC","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/StanfordASL%2FBaRC/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/StanfordASL%2FBaRC/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/StanfordASL%2FBaRC/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/StanfordASL","download_url":"https://codeload.github.com/StanfordASL/BaRC/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":253815073,"owners_count":21968563,"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":["curriculum-learning","dynamical-systems","reinforcement-learning"],"created_at":"2024-12-14T07:13:10.484Z","updated_at":"2025-05-12T20:19:34.854Z","avatar_url":"https://github.com/StanfordASL.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# BaRC: Backward Reachability Curriculum for Robotic Reinforcement Learning\n\nThis repository contains the code for [BaRC: Backward Reachability Curriculum for Robotic Reinforcement Learning](https://arxiv.org/abs/1806.06161) by Boris Ivanovic, James Harrison, Apoorva Sharma, Mo Chen, and Marco Pavone\n\n## Programming Environment ##\n```\ngit clone https://github.com/StanfordASL/BaRC.git\ncd BaRC             # or wherever you cloned the repo\n\n# openai/baselines requires Python 3.5, so we enforce it too.\nconda create --name backreach python=3.5\nsource activate backreach\npip install numpy matplotlib scipy\n```\n\n## Dependencies ##\nThis repository depends on [OpenAI Gym](https://github.com/openai/gym), [OpenAI Baselines](https://github.com/openai/baselines), and [OpenMPI](https://www.open-mpi.org) (because of Baselines). Further, our code requires MATLAB as well as the [helperOC](https://github.com/HJReachability/helperOC) and [Level Set Methods](http://www.cs.ubc.ca/~mitchell/ToolboxLS) toolboxes for backward reachability computations.\n\nFor a minimal installation, you can install OpenAI Gym and Baselines like so:\n```\ncd gym\npip install -e '.[mujoco,atari,classic_control,robotics]'\n\ncd ../code/baselines\npip install -e .\n```\n\nWith those obtained, you must place our two gym environments `DrivingOrigin-v0` and `PlanarQuad-v0` located in the `gym/` folder into your gym installation. Instructions for how to do this can be found on the OpenAI gym website.\n\nThen, place our modifications to the baselines PPO algorithm into your installation of OpenAI baselines. They are located under `code/baselines/`. For this, you simply replace the `ppo1` folder in the baselines repository with ours.\n\nNow you're ready to use our code. `train.py` is the main runner interface which can be called with command line arguments.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fstanfordasl%2Fbarc","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fstanfordasl%2Fbarc","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fstanfordasl%2Fbarc/lists"}