{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:WYN2UXNGBCTKYZJQPGCLUHM6XC","short_pith_number":"pith:WYN2UXNG","schema_version":"1.0","canonical_sha256":"b61baa5da608a6ac65307984ba1d9eb88dbdde50217493c3405e169e3f49fbdc","source":{"kind":"arxiv","id":"2010.08843","version":2},"attestation_state":"computed","paper":{"title":"Approximate information state for approximate planning and reinforcement learning in partially observed systems","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.SY","eess.SY","math.OC"],"primary_cat":"cs.LG","authors_text":"Aditya Mahajan, Amit Sinha, Jayakumar Subramanian, Raihan Seraj","submitted_at":"2020-10-17T18:30:30Z","abstract_excerpt":"We propose a theoretical framework for approximate planning and learning in partially observed systems. Our framework is based on the fundamental notion of information state. We provide two equivalent definitions of information state -- i) a function of history which is sufficient to compute the expected reward and predict its next value; ii) equivalently, a function of the history which can be recursively updated and is sufficient to compute the expected reward and predict the next observation. An information state always leads to a dynamic programming decomposition. Our key result is to show"},"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":"2010.08843","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2020-10-17T18:30:30Z","cross_cats_sorted":["cs.SY","eess.SY","math.OC"],"title_canon_sha256":"e0fe5c6d2bccc47c5a2c945c9c1e9a1bcc5f2b3979200d73bc320ded94ad5951","abstract_canon_sha256":"9cf5cf56ae82bc9b9b5f6ab545c32a362b496e45b767eeabaad5a996b3a0f603"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:11:26.287327Z","signature_b64":"uvhvMqcS+zLvMweGkpZTHUncwGba2ehwfrPGoo++XjHjRzaU4W55UDk3gNJj8OAJJDX+kMTPW7cuVHV/6oaPDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b61baa5da608a6ac65307984ba1d9eb88dbdde50217493c3405e169e3f49fbdc","last_reissued_at":"2026-07-05T03:11:26.286803Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:11:26.286803Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Approximate information state for approximate planning and reinforcement learning in partially observed systems","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.SY","eess.SY","math.OC"],"primary_cat":"cs.LG","authors_text":"Aditya Mahajan, Amit Sinha, Jayakumar Subramanian, Raihan Seraj","submitted_at":"2020-10-17T18:30:30Z","abstract_excerpt":"We propose a theoretical framework for approximate planning and learning in partially observed systems. Our framework is based on the fundamental notion of information state. We provide two equivalent definitions of information state -- i) a function of history which is sufficient to compute the expected reward and predict its next value; ii) equivalently, a function of the history which can be recursively updated and is sufficient to compute the expected reward and predict the next observation. An information state always leads to a dynamic programming decomposition. Our key result is to show"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.08843","kind":"arxiv","version":2},"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/2010.08843/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":"2010.08843","created_at":"2026-07-05T03:11:26.286882+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.08843v2","created_at":"2026-07-05T03:11:26.286882+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.08843","created_at":"2026-07-05T03:11:26.286882+00:00"},{"alias_kind":"pith_short_12","alias_value":"WYN2UXNGBCTK","created_at":"2026-07-05T03:11:26.286882+00:00"},{"alias_kind":"pith_short_16","alias_value":"WYN2UXNGBCTKYZJQ","created_at":"2026-07-05T03:11:26.286882+00:00"},{"alias_kind":"pith_short_8","alias_value":"WYN2UXNG","created_at":"2026-07-05T03:11:26.286882+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.19140","citing_title":"Learning to Hand Off: Provably Convergent Workflow Learning under Interface Constraints","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WYN2UXNGBCTKYZJQPGCLUHM6XC","json":"https://pith.science/pith/WYN2UXNGBCTKYZJQPGCLUHM6XC.json","graph_json":"https://pith.science/api/pith-number/WYN2UXNGBCTKYZJQPGCLUHM6XC/graph.json","events_json":"https://pith.science/api/pith-number/WYN2UXNGBCTKYZJQPGCLUHM6XC/events.json","paper":"https://pith.science/paper/WYN2UXNG"},"agent_actions":{"view_html":"https://pith.science/pith/WYN2UXNGBCTKYZJQPGCLUHM6XC","download_json":"https://pith.science/pith/WYN2UXNGBCTKYZJQPGCLUHM6XC.json","view_paper":"https://pith.science/paper/WYN2UXNG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.08843&json=true","fetch_graph":"https://pith.science/api/pith-number/WYN2UXNGBCTKYZJQPGCLUHM6XC/graph.json","fetch_events":"https://pith.science/api/pith-number/WYN2UXNGBCTKYZJQPGCLUHM6XC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WYN2UXNGBCTKYZJQPGCLUHM6XC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WYN2UXNGBCTKYZJQPGCLUHM6XC/action/storage_attestation","attest_author":"https://pith.science/pith/WYN2UXNGBCTKYZJQPGCLUHM6XC/action/author_attestation","sign_citation":"https://pith.science/pith/WYN2UXNGBCTKYZJQPGCLUHM6XC/action/citation_signature","submit_replication":"https://pith.science/pith/WYN2UXNGBCTKYZJQPGCLUHM6XC/action/replication_record"}},"created_at":"2026-07-05T03:11:26.286882+00:00","updated_at":"2026-07-05T03:11:26.286882+00:00"}