{"id":44583161,"url":"https://github.com/rr-learning/trifinger-rl-example","last_synced_at":"2026-02-14T05:57:10.475Z","repository":{"id":112320618,"uuid":"607183435","full_name":"rr-learning/trifinger-rl-example","owner":"rr-learning","description":"Example package for submission of a reinforcement learning policy to a cluster of TriFinger robots.","archived":false,"fork":false,"pushed_at":"2025-07-25T13:17:56.000Z","size":525,"stargazers_count":3,"open_issues_count":0,"forks_count":2,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-07-25T20:17:21.006Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"bsd-3-clause","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/rr-learning.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,"zenodo":null}},"created_at":"2023-02-27T13:42:38.000Z","updated_at":"2025-07-25T13:18:01.000Z","dependencies_parsed_at":"2025-07-25T15:17:45.999Z","dependency_job_id":"20ced202-a0ec-4723-bb81-3041717bb516","html_url":"https://github.com/rr-learning/trifinger-rl-example","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/rr-learning/trifinger-rl-example","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rr-learning%2Ftrifinger-rl-example","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rr-learning%2Ftrifinger-rl-example/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rr-learning%2Ftrifinger-rl-example/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rr-learning%2Ftrifinger-rl-example/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/rr-learning","download_url":"https://codeload.github.com/rr-learning/trifinger-rl-example/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rr-learning%2Ftrifinger-rl-example/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29438641,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-14T05:24:35.651Z","status":"ssl_error","status_checked_at":"2026-02-14T05:24:34.830Z","response_time":53,"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":"2026-02-14T05:57:10.374Z","updated_at":"2026-02-14T05:57:10.457Z","avatar_url":"https://github.com/rr-learning.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"TriFinger RL Example Package\n============================\n\nThis is an example package that provides expert reinforcement learning policies that can be run on the [TriFinger robot cluster](https://webdav.tuebingen.mpg.de/trifinger/).\nYou can use it as base for your own package when submitting to the robot cluster. The [documentation](https://webdav.tuebingen.mpg.de/trifinger-rl/docs/) for the \nTriFinger RL Datasets provides more information on how to get an account for and submit to the robot cluster.\n\n## Installation\n\nTo install the package run with python 3.8 in the root directory of the repository (we recommend doing this in a virtual environment):\n\n```bash\npip install --upgrade pip  # make sure the most recent version of pip is installed\npip install .\n```\n\nExample Policies\n----------------\n\nThe package contains two expert policies that were used to record the expert datasets for the Push and Lift tasks in the TriFinger RL datasets.\n\nFor the push task:\n\n    $ python3 -m trifinger_rl_datasets.evaluate_sim push trifinger_rl_example.example.TorchPushPolicy --n-episodes=3 -v\n\nFor the lift task:\n\n    $ python3 -m trifinger_rl_datasets.evaluate_sim lift trifinger_rl_example.example.TorchLiftPolicy --n-episodes=3 -v\n\nThe policy classes are implemented in `trifinger_rl_example/example.py`.  The corresponding torch\nmodels are in `trifinger_rl_example/policies` and are installed as package_data so they can be loaded\nat runtime (see `setup.cfg`).\n\nAll training checkpoints of the expert policies are available [here](https://edmond.mpdl.mpg.de/dataset.xhtml?persistentId=doi:10.17617/3.JA8ZW4). They can be\nused with this repository by swapping them with the files in the `policies` subdirectory.\n\nDocumentation\n-------------\n\nFor more information, please see the [software\ndocumentation for the TriFinger RL datasets](https://webdav.tuebingen.mpg.de/trifinger-rl/docs/).\n\n## How to cite\n\nThe expert policies were introduced in the paper [\"Benchmarking Offline Reinforcement Learning on Real-Robot Hardware\"](https://openreview.net/pdf?id=3k5CUGDLNdd):\n\n```\n@inproceedings{\nguertler2023benchmarking,\ntitle={Benchmarking Offline Reinforcement Learning on Real-Robot Hardware},\nauthor={Nico G{\\\"u}rtler and Sebastian Blaes and Pavel Kolev and Felix Widmaier and Manuel Wuthrich and Stefan Bauer and Bernhard Sch{\\\"o}lkopf and Georg Martius},\nbooktitle={The Eleventh International Conference on Learning Representations },\nyear={2023},\nurl={https://openreview.net/forum?id=3k5CUGDLNdd}\n}\n```\n\nThe training pipeline for the expert policies was based on the code of the paper [\"Transferring dexterous manipulation from GPU simulation to a remote real-world trifinger\" by Allshire et al.](https://ieeexplore.ieee.org/abstract/document/9981458).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frr-learning%2Ftrifinger-rl-example","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Frr-learning%2Ftrifinger-rl-example","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frr-learning%2Ftrifinger-rl-example/lists"}