{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HW7PSKUM6Y5OJD6EZ4NWWKHECH","short_pith_number":"pith:HW7PSKUM","schema_version":"1.0","canonical_sha256":"3dbef92a8cf63ae48fc4cf1b6b28e411e4386abe8c1f081ceef24c5699cd6106","source":{"kind":"arxiv","id":"2411.11511","version":1},"attestation_state":"computed","paper":{"title":"Structure learning with Temporal Gaussian Mixture for model-based Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Howard Bowman, Marek Grze\\'s, Th\\'eophile Champion","submitted_at":"2024-11-18T12:16:03Z","abstract_excerpt":"Model-based reinforcement learning refers to a set of approaches capable of sample-efficient decision making, which create an explicit model of the environment. This model can subsequently be used for learning optimal policies. In this paper, we propose a temporal Gaussian Mixture Model composed of a perception model and a transition model. The perception model extracts discrete (latent) states from continuous observations using a variational Gaussian mixture likelihood. Importantly, our model constantly monitors the collected data searching for new Gaussian components, i.e., the perception mo"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2411.11511","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-18T12:16:03Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"1ecc7935cc9677dec654cb05f731fbd35f47cb5bac0e49ead0b8bb702e58efa8","abstract_canon_sha256":"662b7939ba69112dbe949217164163e641dbf43338202f772366a36425bb148f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:36:57.369729Z","signature_b64":"907SjaOophUQzpdPXtPd+9ZlPygXu2nYRhqtsD9IfBTHOFIqquaH0nA407k6hQ8yGj9FMEGlJTAGT9V3RCgCDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3dbef92a8cf63ae48fc4cf1b6b28e411e4386abe8c1f081ceef24c5699cd6106","last_reissued_at":"2026-07-05T09:36:57.369221Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:36:57.369221Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Structure learning with Temporal Gaussian Mixture for model-based Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Howard Bowman, Marek Grze\\'s, Th\\'eophile Champion","submitted_at":"2024-11-18T12:16:03Z","abstract_excerpt":"Model-based reinforcement learning refers to a set of approaches capable of sample-efficient decision making, which create an explicit model of the environment. This model can subsequently be used for learning optimal policies. In this paper, we propose a temporal Gaussian Mixture Model composed of a perception model and a transition model. The perception model extracts discrete (latent) states from continuous observations using a variational Gaussian mixture likelihood. Importantly, our model constantly monitors the collected data searching for new Gaussian components, i.e., the perception mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.11511","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2411.11511/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2411.11511","created_at":"2026-07-05T09:36:57.369278+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.11511v1","created_at":"2026-07-05T09:36:57.369278+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.11511","created_at":"2026-07-05T09:36:57.369278+00:00"},{"alias_kind":"pith_short_12","alias_value":"HW7PSKUM6Y5O","created_at":"2026-07-05T09:36:57.369278+00:00"},{"alias_kind":"pith_short_16","alias_value":"HW7PSKUM6Y5OJD6E","created_at":"2026-07-05T09:36:57.369278+00:00"},{"alias_kind":"pith_short_8","alias_value":"HW7PSKUM","created_at":"2026-07-05T09:36:57.369278+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.24784","citing_title":"AXIOM: Learning to Play Games in Minutes with Expanding Object-Centric Models","ref_index":52,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HW7PSKUM6Y5OJD6EZ4NWWKHECH","json":"https://pith.science/pith/HW7PSKUM6Y5OJD6EZ4NWWKHECH.json","graph_json":"https://pith.science/api/pith-number/HW7PSKUM6Y5OJD6EZ4NWWKHECH/graph.json","events_json":"https://pith.science/api/pith-number/HW7PSKUM6Y5OJD6EZ4NWWKHECH/events.json","paper":"https://pith.science/paper/HW7PSKUM"},"agent_actions":{"view_html":"https://pith.science/pith/HW7PSKUM6Y5OJD6EZ4NWWKHECH","download_json":"https://pith.science/pith/HW7PSKUM6Y5OJD6EZ4NWWKHECH.json","view_paper":"https://pith.science/paper/HW7PSKUM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.11511&json=true","fetch_graph":"https://pith.science/api/pith-number/HW7PSKUM6Y5OJD6EZ4NWWKHECH/graph.json","fetch_events":"https://pith.science/api/pith-number/HW7PSKUM6Y5OJD6EZ4NWWKHECH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HW7PSKUM6Y5OJD6EZ4NWWKHECH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HW7PSKUM6Y5OJD6EZ4NWWKHECH/action/storage_attestation","attest_author":"https://pith.science/pith/HW7PSKUM6Y5OJD6EZ4NWWKHECH/action/author_attestation","sign_citation":"https://pith.science/pith/HW7PSKUM6Y5OJD6EZ4NWWKHECH/action/citation_signature","submit_replication":"https://pith.science/pith/HW7PSKUM6Y5OJD6EZ4NWWKHECH/action/replication_record"}},"created_at":"2026-07-05T09:36:57.369278+00:00","updated_at":"2026-07-05T09:36:57.369278+00:00"}