{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/symmetry-based-disentangled-representation","title":"Symmetry-Based Disentangled Representation Learning requires Interaction with Environments","arxiv_id":"1904.00243","date":"2019-03-30","proceeding":"NeurIPS 2019 12","authors":["Hugo Caselles-Dupré","Michael Garcia-Ortiz","David Filliat"],"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 static observations: agents should interact with the environment to discover its symmetries. Our experiments can be reproduced in Colab and the code is available on GitHub.","url_abs":"https://arxiv.org/abs/1904.00243v3","url_pdf":"https://arxiv.org/pdf/1904.00243v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"symmetry-based-disentangled-representation","repo_url":"https://github.com/Caselles/NeurIPS19-SBDRL","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.00243","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.00243"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Caselles/NeurIPS19-SBDRL","reach":null}],"summary":{"ran_draft_wrong":1,"unverified":4},"by_repo_kind":{"official":{"samples":5,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"a35694e57f6bf223","entry":"translate_action","repo":"Caselles/NeurIPS19-SBDRL","repo_kind":"official","path":"code/symmetry_based_disentanglement_a_la_WM/interactive_demo_WM.py","file_url":"https://github.com/Caselles/NeurIPS19-SBDRL/blob/HEAD/code/symmetry_based_disentanglement_a_la_WM/interactive_demo_WM.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a35694e57f6bf223"}},{"code_sha256_prefix":"4ea78db60dcc3a18","entry":"loss_fn","repo":"Caselles/NeurIPS19-SBDRL","repo_kind":"official","path":"code/learn_4_dim_linear_disentangled_representation/01_train_vae_sans_cos_sin.py","file_url":"https://github.com/Caselles/NeurIPS19-SBDRL/blob/HEAD/code/learn_4_dim_linear_disentangled_representation/01_train_vae_sans_cos_sin.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4ea78db60dcc3a18"}},{"code_sha256_prefix":"589b55333db1f14b","entry":"loss_fn_predict_next_z","repo":"Caselles/NeurIPS19-SBDRL","repo_kind":"official","path":"code/learn_4_dim_linear_disentangled_representation/01_train_vae_sans_cos_sin.py","file_url":"https://github.com/Caselles/NeurIPS19-SBDRL/blob/HEAD/code/learn_4_dim_linear_disentangled_representation/01_train_vae_sans_cos_sin.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"589b55333db1f14b"}},{"code_sha256_prefix":"aa7ead8e6add08d7","entry":"set_relevant_grad_to_zero","repo":"Caselles/NeurIPS19-SBDRL","repo_kind":"official","path":"code/learn_4_dim_linear_disentangled_representation/01_train_vae_sans_cos_sin.py","file_url":"https://github.com/Caselles/NeurIPS19-SBDRL/blob/HEAD/code/learn_4_dim_linear_disentangled_representation/01_train_vae_sans_cos_sin.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"aa7ead8e6add08d7"}},{"code_sha256_prefix":"5c811211b32a7620","entry":"train_batch","repo":"Caselles/NeurIPS19-SBDRL","repo_kind":"official","path":"code/reproduction_exp_CCI_VAE/01_train_vae.py","file_url":"https://github.com/Caselles/NeurIPS19-SBDRL/blob/HEAD/code/reproduction_exp_CCI_VAE/01_train_vae.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5c811211b32a7620"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}