{"id":16023745,"url":"https://github.com/vikashplus/mabel","last_synced_at":"2025-07-18T15:37:50.706Z","repository":{"id":67081393,"uuid":"255467999","full_name":"vikashplus/mabel","owner":"vikashplus","description":"Manipulation Benchmarks for Learning","archived":false,"fork":false,"pushed_at":"2020-06-11T14:55:30.000Z","size":1909,"stargazers_count":4,"open_issues_count":0,"forks_count":1,"subscribers_count":5,"default_branch":"master","last_synced_at":"2025-04-09T15:57:09.198Z","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":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/vikashplus.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":"2020-04-14T00:01:03.000Z","updated_at":"2021-10-25T13:10:06.000Z","dependencies_parsed_at":null,"dependency_job_id":"d4ad45cf-6a5e-41ea-82bc-4add9446d136","html_url":"https://github.com/vikashplus/mabel","commit_stats":{"total_commits":12,"total_committers":2,"mean_commits":6.0,"dds":0.5,"last_synced_commit":"0ed78083860ff02c52bacce6c09fb0b34aa79a8d"},"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/vikashplus/mabel","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vikashplus%2Fmabel","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vikashplus%2Fmabel/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vikashplus%2Fmabel/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vikashplus%2Fmabel/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/vikashplus","download_url":"https://codeload.github.com/vikashplus/mabel/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/vikashplus%2Fmabel/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":265787155,"owners_count":23828374,"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":[],"created_at":"2024-10-08T19:02:17.467Z","updated_at":"2025-07-18T15:37:50.684Z","avatar_url":"https://github.com/vikashplus.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# MABEL\nMAnipulation BEnchmarks for Learning\n\n`MABEL` is a collection of environments/tasks for benchmarking manipulation, simulated with the [Mujoco](http://www.mujoco.org/) physics engine and wrapped in the [OpenAI `gym`](https://gym.openai.com/) API. 'MABEL' constains following tasks\n\nPointing           | Pouring       | Relocation             | Zipping\n:-------------------------:|:-------------------------:|:-------------------------:|:-------------------------:\n![Alt text](mabel/mabel_envs/reach/reach.png?raw=false \"Fetch Reaching\") |  ![Alt text](mabel/mabel_envs/pouring/pouring.png?raw=false \"Liquid pouring\") | ![Alt text](mabel/mabel_envs/relocate/relocate.png?raw=false \"Object relocation\") | ![Alt text](mabel/mabel_envs/zipper/zipper.png?raw=false \"Fetch zipper\")\n\n\n## Getting Started\n`MABEL` uses git submodules to resolve dependencies. Please follow steps exactly as below to install correctly.\n\n0. Ensure you have access these repositories - [Franka_sim](https://github.com/vikashplus/franka_sim), [Furniture_sim](https://github.com/vikashplus/furniture_sim) and [Scene_sim](https://github.com/vikashplus/scene_sim)\n\n1. Clone this repo with pre-populated submodule dependencies\n```\n$ git clone --recursive git@github.com:vikashplus/mabel.git\n```\n2. Update submodules\n```\n$ cd mabel  \n$ git submodule update --remote\n```\n3. Add repo to pythonpath by updating `~/.bashrc` or `~/.bash_profile`\n```\nexport PYTHONPATH=\"\u003cpath/to/mabel\u003e:$PYTHONPATH\"\n```\n4. Follow install instructions from [mjrl](https://github.com/aravindr93/mjrl) to get model free agents for `MABEL`\n5. To visualize an env using a random policy\n```\nMJPL python mabel/mabel_agents/mjrl/examine_policy.py -i mabel -e MableReachRandom-v0\n```\n5. To visualize a trained `mjrl` agent's policy\n```\nMJPL python mabel/mabel_agents/mjrl/examine_policy.py -i mabel -e MableReachRandom-v0 -p \u003cpath to policy\u003e\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvikashplus%2Fmabel","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fvikashplus%2Fmabel","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fvikashplus%2Fmabel/lists"}