{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VBPH2HOFGCFWAF4GNQUHKTZKV4","short_pith_number":"pith:VBPH2HOF","schema_version":"1.0","canonical_sha256":"a85e7d1dc5308b6017866c28754f2aaf3b9a878d41b11221a81d2f8c3867c3a0","source":{"kind":"arxiv","id":"2302.14509","version":2},"attestation_state":"computed","paper":{"title":"Policy Dispersion in Non-Markovian Environment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bohao Qu, Chang Yi, Hechang Chen, Ivor W.Tsang, Jielong Yang, Xiaofeng Cao, Yew-Soon Ong","submitted_at":"2023-02-28T11:58:39Z","abstract_excerpt":"Markov Decision Process (MDP) presents a mathematical framework to formulate the learning processes of agents in reinforcement learning. MDP is limited by the Markovian assumption that a reward only depends on the immediate state and action. However, a reward sometimes depends on the history of states and actions, which may result in the decision process in a non-Markovian environment. In such environments, agents receive rewards via temporally-extended behaviors sparsely, and the learned policies may be similar. This leads the agents acquired with similar policies generally overfit to the giv"},"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":"2302.14509","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-28T11:58:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"709b9e82e17e3d4a263bf80cc3bf5213ad17ba4e625ee275c824f98d86d6fba9","abstract_canon_sha256":"ddf718ff15e61dedcc2690f9eb17d5dad0220cfc8751ffe3455dff03ad2abb0c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:26:10.776093Z","signature_b64":"n7co1/KJbtXwgRMdmAriJ9lDku+GNaMwoCXkRnwT5YRQPge2WSMy5bkEYDydNfOlwQmYUDQH8F5mGFFvAldQCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a85e7d1dc5308b6017866c28754f2aaf3b9a878d41b11221a81d2f8c3867c3a0","last_reissued_at":"2026-07-05T08:26:10.775622Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:26:10.775622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Policy Dispersion in Non-Markovian Environment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bohao Qu, Chang Yi, Hechang Chen, Ivor W.Tsang, Jielong Yang, Xiaofeng Cao, Yew-Soon Ong","submitted_at":"2023-02-28T11:58:39Z","abstract_excerpt":"Markov Decision Process (MDP) presents a mathematical framework to formulate the learning processes of agents in reinforcement learning. MDP is limited by the Markovian assumption that a reward only depends on the immediate state and action. However, a reward sometimes depends on the history of states and actions, which may result in the decision process in a non-Markovian environment. In such environments, agents receive rewards via temporally-extended behaviors sparsely, and the learned policies may be similar. This leads the agents acquired with similar policies generally overfit to the giv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.14509","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/2302.14509/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":"2302.14509","created_at":"2026-07-05T08:26:10.775683+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.14509v2","created_at":"2026-07-05T08:26:10.775683+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.14509","created_at":"2026-07-05T08:26:10.775683+00:00"},{"alias_kind":"pith_short_12","alias_value":"VBPH2HOFGCFW","created_at":"2026-07-05T08:26:10.775683+00:00"},{"alias_kind":"pith_short_16","alias_value":"VBPH2HOFGCFWAF4G","created_at":"2026-07-05T08:26:10.775683+00:00"},{"alias_kind":"pith_short_8","alias_value":"VBPH2HOF","created_at":"2026-07-05T08:26:10.775683+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/VBPH2HOFGCFWAF4GNQUHKTZKV4","json":"https://pith.science/pith/VBPH2HOFGCFWAF4GNQUHKTZKV4.json","graph_json":"https://pith.science/api/pith-number/VBPH2HOFGCFWAF4GNQUHKTZKV4/graph.json","events_json":"https://pith.science/api/pith-number/VBPH2HOFGCFWAF4GNQUHKTZKV4/events.json","paper":"https://pith.science/paper/VBPH2HOF"},"agent_actions":{"view_html":"https://pith.science/pith/VBPH2HOFGCFWAF4GNQUHKTZKV4","download_json":"https://pith.science/pith/VBPH2HOFGCFWAF4GNQUHKTZKV4.json","view_paper":"https://pith.science/paper/VBPH2HOF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.14509&json=true","fetch_graph":"https://pith.science/api/pith-number/VBPH2HOFGCFWAF4GNQUHKTZKV4/graph.json","fetch_events":"https://pith.science/api/pith-number/VBPH2HOFGCFWAF4GNQUHKTZKV4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VBPH2HOFGCFWAF4GNQUHKTZKV4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VBPH2HOFGCFWAF4GNQUHKTZKV4/action/storage_attestation","attest_author":"https://pith.science/pith/VBPH2HOFGCFWAF4GNQUHKTZKV4/action/author_attestation","sign_citation":"https://pith.science/pith/VBPH2HOFGCFWAF4GNQUHKTZKV4/action/citation_signature","submit_replication":"https://pith.science/pith/VBPH2HOFGCFWAF4GNQUHKTZKV4/action/replication_record"}},"created_at":"2026-07-05T08:26:10.775683+00:00","updated_at":"2026-07-05T08:26:10.775683+00:00"}