{"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/learning-robust-dynamics-through-variational","title":"Learning Robust Dynamics through Variational Sparse Gating","arxiv_id":"2210.11698","date":"2022-10-21","proceeding":null,"authors":["Arnav Kumar Jain","Shivakanth Sujit","Shruti Joshi","Vincent Michalski","Danijar Hafner","Samira Ebrahimi-Kahou"],"abstract":"Learning world models from their sensory inputs enables agents to plan for actions by imagining their future outcomes. World models have previously been shown to improve sample-efficiency in simulated environments with few objects, but have not yet been applied successfully to environments with many objects. In environments with many objects, often only a small number of them are moving or interacting at the same time. In this paper, we investigate integrating this inductive bias of sparse interactions into the latent dynamics of world models trained from pixels. First, we introduce Variational Sparse Gating (VSG), a latent dynamics model that updates its feature dimensions sparsely through stochastic binary gates. Moreover, we propose a simplified architecture Simple Variational Sparse Gating (SVSG) that removes the deterministic pathway of previous models, resulting in a fully stochastic transition function that leverages the VSG mechanism. We evaluate the two model architectures in the BringBackShapes (BBS) environment that features a large number of moving objects and partial observability, demonstrating clear improvements over prior models.","url_abs":"https://arxiv.org/abs/2210.11698v1","url_pdf":"https://arxiv.org/pdf/2210.11698v1.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":"learning-robust-dynamics-through-variational","repo_url":"https://github.com/arnavkj1995/vsg","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"inductive-bias","task_name":"Inductive Bias"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2210.11698","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.11698"}},"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/arnavkj1995/vsg","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":1,"unverified":6},"by_repo_kind":{"official":{"samples":7,"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":"b7ff9ef9697d35f1","entry":"count_steps","repo":"arnavkj1995/vsg","repo_kind":"official","path":"dreamer.py","file_url":"https://github.com/arnavkj1995/vsg/blob/HEAD/dreamer.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b7ff9ef9697d35f1"}},{"code_sha256_prefix":"9b634707bba3591e","entry":"compute_scores","repo":"arnavkj1995/vsg","repo_kind":"official","path":"tools.py","file_url":"https://github.com/arnavkj1995/vsg/blob/HEAD/tools.py","link_basis":"harvester_set","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":"9b634707bba3591e"}},{"code_sha256_prefix":"31412a30221aa524","entry":"graph_summary","repo":"arnavkj1995/vsg","repo_kind":"official","path":"tools.py","file_url":"https://github.com/arnavkj1995/vsg/blob/HEAD/tools.py","link_basis":"harvester_set","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":"31412a30221aa524"}},{"code_sha256_prefix":"f5538829a09b5fc7","entry":"load_baselines","repo":"arnavkj1995/vsg","repo_kind":"official","path":"plotting.py","file_url":"https://github.com/arnavkj1995/vsg/blob/HEAD/plotting.py","link_basis":"harvester_set","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":"f5538829a09b5fc7"}},{"code_sha256_prefix":"22c3f55cbb21523d","entry":"load_run","repo":"arnavkj1995/vsg","repo_kind":"official","path":"plotting.py","file_url":"https://github.com/arnavkj1995/vsg/blob/HEAD/plotting.py","link_basis":"harvester_set","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":"22c3f55cbb21523d"}},{"code_sha256_prefix":"151b79dfa34b9b00","entry":"load_runs","repo":"arnavkj1995/vsg","repo_kind":"official","path":"plotting.py","file_url":"https://github.com/arnavkj1995/vsg/blob/HEAD/plotting.py","link_basis":"harvester_set","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":"151b79dfa34b9b00"}},{"code_sha256_prefix":"669829564c1e4780","entry":"var_nest_names","repo":"arnavkj1995/vsg","repo_kind":"official","path":"tools.py","file_url":"https://github.com/arnavkj1995/vsg/blob/HEAD/tools.py","link_basis":"harvester_set","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":"669829564c1e4780"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}