{"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/unsupervised-learning-of-temporal","title":"Unsupervised Learning of Temporal Abstractions with Slot-based Transformers","arxiv_id":"2203.13573","date":"2022-03-25","proceeding":null,"authors":["Anand Gopalakrishnan","Kazuki Irie","Jürgen Schmidhuber","Sjoerd van Steenkiste"],"abstract":"The discovery of reusable sub-routines simplifies decision-making and planning in complex reinforcement learning problems. Previous approaches propose to learn such temporal abstractions in a purely unsupervised fashion through observing state-action trajectories gathered from executing a policy. However, a current limitation is that they process each trajectory in an entirely sequential manner, which prevents them from revising earlier decisions about sub-routine boundary points in light of new incoming information. In this work we propose SloTTAr, a fully parallel approach that integrates sequence processing Transformers with a Slot Attention module and adaptive computation for learning about the number of such sub-routines in an unsupervised fashion. We demonstrate how SloTTAr is capable of outperforming strong baselines in terms of boundary point discovery, even for sequences containing variable amounts of sub-routines, while being up to 7x faster to train on existing benchmarks.","url_abs":"https://arxiv.org/abs/2203.13573v2","url_pdf":"https://arxiv.org/pdf/2203.13573v2.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":"unsupervised-learning-of-temporal","repo_url":"https://github.com/agopal42/slottar","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"decision-making","task_name":"Decision Making"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2203.13573","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.13573"}},"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/agopal42/slottar","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":1,"unverified":7},"by_repo_kind":{"official":{"samples":8,"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":"7816c6d65ab55d8f","entry":"get_angles","repo":"agopal42/slottar","repo_kind":"official","path":"slottar_modules.py","file_url":"https://github.com/agopal42/slottar/blob/HEAD/slottar_modules.py","link_basis":"plan_row","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":"7816c6d65ab55d8f"}},{"code_sha256_prefix":"2fde1372d5034b2e","entry":"build_seq","repo":"agopal42/slottar","repo_kind":"official","path":"slottar_modules.py","file_url":"https://github.com/agopal42/slottar/blob/HEAD/slottar_modules.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":"2fde1372d5034b2e"}},{"code_sha256_prefix":"e38b375ee5c1bc1d","entry":"compute_geometric","repo":"agopal42/slottar","repo_kind":"official","path":"utils.py","file_url":"https://github.com/agopal42/slottar/blob/HEAD/utils.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":"e38b375ee5c1bc1d"}},{"code_sha256_prefix":"a40c36a3801e0a48","entry":"create_padding_mask","repo":"agopal42/slottar","repo_kind":"official","path":"slottar_modules.py","file_url":"https://github.com/agopal42/slottar/blob/HEAD/slottar_modules.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":"a40c36a3801e0a48"}},{"code_sha256_prefix":"98d89b921bd24bf2","entry":"gumbel_sample","repo":"agopal42/slottar","repo_kind":"official","path":"baselines_utils.py","file_url":"https://github.com/agopal42/slottar/blob/HEAD/baselines_utils.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":"98d89b921bd24bf2"}},{"code_sha256_prefix":"58e1bcada748d451","entry":"kl_div","repo":"agopal42/slottar","repo_kind":"official","path":"utils.py","file_url":"https://github.com/agopal42/slottar/blob/HEAD/utils.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":"58e1bcada748d451"}},{"code_sha256_prefix":"ca4ef00b5db7d896","entry":"prepare_dataset","repo":"agopal42/slottar","repo_kind":"official","path":"preprocess.py","file_url":"https://github.com/agopal42/slottar/blob/HEAD/preprocess.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":"ca4ef00b5db7d896"}},{"code_sha256_prefix":"8d63f384045362b9","entry":"to_one_hot","repo":"agopal42/slottar","repo_kind":"official","path":"baselines_utils.py","file_url":"https://github.com/agopal42/slottar/blob/HEAD/baselines_utils.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":"8d63f384045362b9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}