{"id":17581372,"url":"https://github.com/caselles/neurips19-sbdrl","last_synced_at":"2025-08-17T18:38:27.507Z","repository":{"id":122516579,"uuid":"207809415","full_name":"Caselles/NeurIPS19-SBDRL","owner":"Caselles","description":"Code for NeurIPS 2019 paper: \"Symmetry-Based Disentangled Representation Learning requires Interaction with Environments\" by H. Caselles-Dupré, M. Garcia-Ortiz and D. Filliat.","archived":false,"fork":false,"pushed_at":"2019-12-09T01:14:47.000Z","size":6406,"stargazers_count":35,"open_issues_count":0,"forks_count":11,"subscribers_count":4,"default_branch":"master","last_synced_at":"2025-06-03T01:51:28.841Z","etag":null,"topics":[],"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/Caselles.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":"2019-09-11T12:40:41.000Z","updated_at":"2024-10-02T11:03:55.000Z","dependencies_parsed_at":null,"dependency_job_id":"06edc13f-f9d4-4c2d-9590-11d5315400c6","html_url":"https://github.com/Caselles/NeurIPS19-SBDRL","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/Caselles/NeurIPS19-SBDRL","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Caselles%2FNeurIPS19-SBDRL","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Caselles%2FNeurIPS19-SBDRL/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Caselles%2FNeurIPS19-SBDRL/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Caselles%2FNeurIPS19-SBDRL/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Caselles","download_url":"https://codeload.github.com/Caselles/NeurIPS19-SBDRL/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Caselles%2FNeurIPS19-SBDRL/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":261972888,"owners_count":23238539,"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":"2024-10-22T01:08:40.449Z","updated_at":"2025-06-25T23:32:03.404Z","avatar_url":"https://github.com/Caselles.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Code for NeurIPS 2019 paper.\n\u003ch1 align=\"center\"\u003e \u003ci\u003e \u003cb\u003e \"Symmetry-Based Disentangled Representation Learning requires Interaction with Environments\" \u003c/i\u003e \u003c/b\u003e\u003c/h1\u003e\n\nThis repository contains the official code for the NeurIPS 2019 paper \"Symmetry-Based Disentangled Representation Learning requires Interaction with Environments\" by Hugo Caselles-Dupré, Michael Garcia-Ortiz and David Filliat.\n\n\u003e **Symmetry-Based Disentangled Representation Learning requires Interaction with Environments**\u003cbr\u003e\n\u003e Hugo Caselles-Dupré ¹ ², Michael Garcia-Ortiz ² and David Filliat ¹\u003cbr\u003e\n\u003e¹ Flowers Laboratory (ENSTA Paris  \u003cimg width=\"30px\" src=\"static/logo_ensta.png\"\u003e \u0026 INRIA \u003cimg width=\"70px\" src=\"static/logo_inria.png\"\u003e)  \u003cbr\u003e\n\u003e² Softbank Robotics Europe \u003cimg width=\"100px\" src=\"static/sbre.jpg\"\u003e \u003cbr\u003e\n\u003e https://arxiv.org/abs/1904.00243\n\u003e\n\u003e **Abstract:** *Finding a generally accepted formal definition of a disentangled representation in the context of an agent behaving in an environment is an important challenge towards the construction of data-efficient autonomous agents. Higgins et al. recently proposed Symmetry-Based Disentangled Representation Learning, a definition based on a characterization of symmetries in the environment using group theory. We build on their work and make observations, theoretical and empirical, that lead us to argue that Symmetry-Based Disentangled Representation Learning cannot only be based on fixed data samples. Agents should interact with the environment to discover its symmetries.*\n\n\u003cp align=\"center\"\u003e\n  \u003cimg src=\"static/colab_favicon_256px.png\"\u003e\u003cbr\u003e\n  \u003ca href=\"https://colab.research.google.com/drive/1KVlSV24c687N_4TLJWwGTkjt3sh9ufWW\"\u003eOpen Colab Notebook to reproduce paper's experiments.\u003c/a\u003e\n\u003c/p\u003e\n\n------------------------\n\n\n## Resources\n\nAll material related to our paper is available via the following links:\n\n| Link                      | Description\n| :--------------           | :----------\n| [Link ArXiv](https://arxiv.org/abs/1904.00243) | Paper PDF.\n| [Link Project Page](https://sites.google.com/view/sbdrl-neurips19/) | Project page.\n| [Link Video](https://youtu.be/jyN3ZQNH1GI) | Summary video.\n| [Link Colab](https://colab.research.google.com/drive/1KVlSV24c687N_4TLJWwGTkjt3sh9ufWW) | Colab to reproduce experiments.\n| [Link Github](https://github.com/Caselles/Symmetry_based_Disentanglement)  | Source code.\n| [Link Slides](https://github.com/Caselles/NeurIPS19-SBDRL/blob/master/static/%5BNeurIPS19%5D%20SBDRL%20requires%20Interactions%20with%20Environments.pdf) | Presentation slides.\n| [Link Poster](https://github.com/Caselles/NeurIPS19-SBDRL/blob/master/static/_NeurIPS19_Poster__SBDRL_requires_Interactions_w_Env.pdf) | Poster.\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcaselles%2Fneurips19-sbdrl","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcaselles%2Fneurips19-sbdrl","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcaselles%2Fneurips19-sbdrl/lists"}