{"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/sparsely-changing-latent-states-for","title":"Sparsely Changing Latent States for Prediction and Planning in Partially Observable Domains","arxiv_id":"2110.15949","date":"2021-10-29","proceeding":"NeurIPS 2021 12","authors":["Christian Gumbsch","Martin V. Butz","Georg Martius"],"abstract":"A common approach to prediction and planning in partially observable domains is to use recurrent neural networks (RNNs), which ideally develop and maintain a latent memory about hidden, task-relevant factors. We hypothesize that many of these hidden factors in the physical world are constant over time, changing only sparsely. To study this hypothesis, we propose Gated $L_0$ Regularized Dynamics (GateL0RD), a novel recurrent architecture that incorporates the inductive bias to maintain stable, sparsely changing latent states. The bias is implemented by means of a novel internal gating function and a penalty on the $L_0$ norm of latent state changes. We demonstrate that GateL0RD can compete with or outperform state-of-the-art RNNs in a variety of partially observable prediction and control tasks. GateL0RD tends to encode the underlying generative factors of the environment, ignores spurious temporal dependencies, and generalizes better, improving sampling efficiency and overall performance in model-based planning and reinforcement learning tasks. Moreover, we show that the developing latent states can be easily interpreted, which is a step towards better explainability in RNNs.","url_abs":"https://arxiv.org/abs/2110.15949v2","url_pdf":"https://arxiv.org/pdf/2110.15949v2.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":"sparsely-changing-latent-states-for","repo_url":"https://github.com/martius-lab/gatel0rd","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"inductive-bias","task_name":"Inductive Bias"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2110.15949","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.15949"}},"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":"deterministic:regex_extraction","url":"https://github.com/martius-lab/GateL0RD","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/martius-lab/gatel0rd","reach":null}],"summary":{"ran":2,"ran_honours":2},"by_repo_kind":{"official":{"samples":4,"ran":4,"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":"3db6c8c66667e343","entry":"GateL0RDCell","repo":"martius-lab/gatel0rd","repo_kind":"official","path":"gatel0rd.py","file_url":"https://github.com/martius-lab/gatel0rd/blob/HEAD/gatel0rd.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3db6c8c66667e343"}},{"code_sha256_prefix":"c2f3b62d0ac298a6","entry":"HeavisideST","repo":"martius-lab/gatel0rd","repo_kind":"official","path":"gatel0rd.py","file_url":"https://github.com/martius-lab/gatel0rd/blob/HEAD/gatel0rd.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c2f3b62d0ac298a6"}},{"code_sha256_prefix":"f7844d01e9e22d3e","entry":"ReTanh","repo":"martius-lab/GateL0RD","repo_kind":"official","path":"gatel0rd.py","file_url":"https://github.com/martius-lab/GateL0RD/blob/HEAD/gatel0rd.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f7844d01e9e22d3e"}},{"code_sha256_prefix":"fcb0982a11bff486","entry":"ReTanh","repo":"martius-lab/gatel0rd","repo_kind":"official","path":"gatel0rd.py","file_url":"https://github.com/martius-lab/gatel0rd/blob/HEAD/gatel0rd.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fcb0982a11bff486"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}