{"id":21739574,"url":"https://github.com/berkeleyautomation/rlqp_train","last_synced_at":"2026-05-21T05:35:24.190Z","repository":{"id":104388544,"uuid":"378979024","full_name":"BerkeleyAutomation/rlqp_train","owner":"BerkeleyAutomation","description":"Environment and training for RQLP (Accelerating Quadratic Optimization with RL)","archived":false,"fork":false,"pushed_at":"2022-12-07T21:28:44.000Z","size":63,"stargazers_count":3,"open_issues_count":1,"forks_count":0,"subscribers_count":5,"default_branch":"master","last_synced_at":"2025-03-21T00:44:55.852Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"https://berkeleyautomation.github.io/rlqp/","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/BerkeleyAutomation.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":"2021-06-21T15:31:54.000Z","updated_at":"2023-03-19T12:20:34.000Z","dependencies_parsed_at":"2023-03-13T14:57:38.832Z","dependency_job_id":null,"html_url":"https://github.com/BerkeleyAutomation/rlqp_train","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/BerkeleyAutomation/rlqp_train","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BerkeleyAutomation%2Frlqp_train","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BerkeleyAutomation%2Frlqp_train/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BerkeleyAutomation%2Frlqp_train/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BerkeleyAutomation%2Frlqp_train/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/BerkeleyAutomation","download_url":"https://codeload.github.com/BerkeleyAutomation/rlqp_train/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/BerkeleyAutomation%2Frlqp_train/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":33289890,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-21T02:57:32.698Z","status":"ssl_error","status_checked_at":"2026-05-21T02:57:31.990Z","response_time":62,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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":[],"created_at":"2024-11-26T06:09:28.807Z","updated_at":"2026-05-21T05:35:24.148Z","avatar_url":"https://github.com/BerkeleyAutomation.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# IMPORTANT! INCOMPLETE\n\nWe are in the process of cleaning up and migrating research-quality code to this repo.  This repo currently only has an implementation of DDPG, and TD3 is not yet tested.  DDPG, however seems to work well in practice.\n\nFeel free to file an issue with any questions or concerns.\n\n# Submodules\n\n    rlqp_train (this repo, not a fork)\n    +- rlqp_benchmarks  (fork of https://github.com/osqp/osqp_benchmarks)\n    \n# Requirements:\n\nThe RLQP python solver must be separately installed.\n\n    rlqp-python      (fork of https://github.com/osqp/osqp-python)\n    +- rlqp_solver   (fork of https://github.com/osqp/osqp.git)\n       +- qdldl      (https://github.com/osqp/qdldl, not forked)\n\n# Setup instructions\n\n    % git submodule update --init --recursive\n\n\n# Virtualenv Instructions\n\nFor all these instructions, we assume the environment variable `RLQP` is set to the directory in which this README.md file is contained.\n\nCreate a virtual environment (1 time)\n\n    % export RLQP=`pwd`\n    % cd $RLQP\n    % virtualenv venv/rlqp\n\nActivate the virtual environment (run once in each new terminal):\n\n    % . $RLQP/venv/rlqp/bin/activate\n\nCompile and install the RLQP Python wrapper (1 time per git update)\n\n    % pip uninstall -y rlqp\n    % cd $RLQP/rlqp-python\n    % rm -rf build extension/src/*.a osqp_sources/build\n    % python setup.py install\n\nInstall rlqp_benchmarks to the venv:\n\n    % cd $RLQP/rlqp_benchmarks\n    % python setup.py develop\n\nPlace this project in development mode (1 time)\n\n    % cd $RLQP\n    % python setup.py develop\n\n# Example Training:\n\n    % python scripts/train.py\n\n# Monitoring Training with Tensorboard\n\nAssuming logs are being written to a subdirectory in experiments, run (with the virtualenv active):\n\n    % tensorboard --logdir experiments\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fberkeleyautomation%2Frlqp_train","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fberkeleyautomation%2Frlqp_train","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fberkeleyautomation%2Frlqp_train/lists"}