{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2011:BADH7PE4IBP3IASYXQVCLTXWIQ","short_pith_number":"pith:BADH7PE4","schema_version":"1.0","canonical_sha256":"08067fbc9c405fb40258bc2a25cef64417ce52099af5c90d806d92036f401060","source":{"kind":"arxiv","id":"1102.5561","version":2},"attestation_state":"computed","paper":{"title":"Decision Making Agent Searching for Markov Models in Near-Deterministic World","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Andras Lorincz, Gabor Matuz","submitted_at":"2011-02-27T23:47:13Z","abstract_excerpt":"Reinforcement learning has solid foundations, but becomes inefficient in partially observed (non-Markovian) environments. Thus, a learning agent -born with a representation and a policy- might wish to investigate to what extent the Markov property holds. We propose a learning architecture that utilizes combinatorial policy optimization to overcome non-Markovity and to develop efficient behaviors, which are easy to inherit, tests the Markov property of the behavioral states, and corrects against non-Markovity by running a deterministic factored Finite State Model, which can be learned. We illus"},"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":"1102.5561","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2011-02-27T23:47:13Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5fd3b230095b4be2123f396eb42c2eca8fba43407c108567aafd7109334511ff","abstract_canon_sha256":"5698c01ae55ed37a878e611f3035225cb1b224e0edf86e23d6b0c2fb2afa9dfb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:27:37.552065Z","signature_b64":"ZB+RcF4Zb4KHDHNiRUqcc9BnFeL44yghT1/I//6qSDNRxqPLaBXCy5e2w1PdM91A95HqGhQ4k2d2VSXEb/DbCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08067fbc9c405fb40258bc2a25cef64417ce52099af5c90d806d92036f401060","last_reissued_at":"2026-05-18T04:27:37.551385Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:27:37.551385Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Decision Making Agent Searching for Markov Models in Near-Deterministic World","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Andras Lorincz, Gabor Matuz","submitted_at":"2011-02-27T23:47:13Z","abstract_excerpt":"Reinforcement learning has solid foundations, but becomes inefficient in partially observed (non-Markovian) environments. Thus, a learning agent -born with a representation and a policy- might wish to investigate to what extent the Markov property holds. We propose a learning architecture that utilizes combinatorial policy optimization to overcome non-Markovity and to develop efficient behaviors, which are easy to inherit, tests the Markov property of the behavioral states, and corrects against non-Markovity by running a deterministic factored Finite State Model, which can be learned. We illus"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1102.5561","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":""},"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":"1102.5561","created_at":"2026-05-18T04:27:37.551491+00:00"},{"alias_kind":"arxiv_version","alias_value":"1102.5561v2","created_at":"2026-05-18T04:27:37.551491+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1102.5561","created_at":"2026-05-18T04:27:37.551491+00:00"},{"alias_kind":"pith_short_12","alias_value":"BADH7PE4IBP3","created_at":"2026-05-18T12:26:24.575870+00:00"},{"alias_kind":"pith_short_16","alias_value":"BADH7PE4IBP3IASY","created_at":"2026-05-18T12:26:24.575870+00:00"},{"alias_kind":"pith_short_8","alias_value":"BADH7PE4","created_at":"2026-05-18T12:26:24.575870+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BADH7PE4IBP3IASYXQVCLTXWIQ","json":"https://pith.science/pith/BADH7PE4IBP3IASYXQVCLTXWIQ.json","graph_json":"https://pith.science/api/pith-number/BADH7PE4IBP3IASYXQVCLTXWIQ/graph.json","events_json":"https://pith.science/api/pith-number/BADH7PE4IBP3IASYXQVCLTXWIQ/events.json","paper":"https://pith.science/paper/BADH7PE4"},"agent_actions":{"view_html":"https://pith.science/pith/BADH7PE4IBP3IASYXQVCLTXWIQ","download_json":"https://pith.science/pith/BADH7PE4IBP3IASYXQVCLTXWIQ.json","view_paper":"https://pith.science/paper/BADH7PE4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1102.5561&json=true","fetch_graph":"https://pith.science/api/pith-number/BADH7PE4IBP3IASYXQVCLTXWIQ/graph.json","fetch_events":"https://pith.science/api/pith-number/BADH7PE4IBP3IASYXQVCLTXWIQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BADH7PE4IBP3IASYXQVCLTXWIQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BADH7PE4IBP3IASYXQVCLTXWIQ/action/storage_attestation","attest_author":"https://pith.science/pith/BADH7PE4IBP3IASYXQVCLTXWIQ/action/author_attestation","sign_citation":"https://pith.science/pith/BADH7PE4IBP3IASYXQVCLTXWIQ/action/citation_signature","submit_replication":"https://pith.science/pith/BADH7PE4IBP3IASYXQVCLTXWIQ/action/replication_record"}},"created_at":"2026-05-18T04:27:37.551491+00:00","updated_at":"2026-05-18T04:27:37.551491+00:00"}