{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:VBPH2HOFGCFWAF4GNQUHKTZKV4","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"ddf718ff15e61dedcc2690f9eb17d5dad0220cfc8751ffe3455dff03ad2abb0c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-28T11:58:39Z","title_canon_sha256":"709b9e82e17e3d4a263bf80cc3bf5213ad17ba4e625ee275c824f98d86d6fba9"},"schema_version":"1.0","source":{"id":"2302.14509","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.14509","created_at":"2026-07-05T08:26:10Z"},{"alias_kind":"arxiv_version","alias_value":"2302.14509v2","created_at":"2026-07-05T08:26:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.14509","created_at":"2026-07-05T08:26:10Z"},{"alias_kind":"pith_short_12","alias_value":"VBPH2HOFGCFW","created_at":"2026-07-05T08:26:10Z"},{"alias_kind":"pith_short_16","alias_value":"VBPH2HOFGCFWAF4G","created_at":"2026-07-05T08:26:10Z"},{"alias_kind":"pith_short_8","alias_value":"VBPH2HOF","created_at":"2026-07-05T08:26:10Z"}],"graph_snapshots":[{"event_id":"sha256:ffec12cfb790506fd05a88f2a2efb09b2083e18e47787bd8c12c413ac60e361c","target":"graph","created_at":"2026-07-05T08:26:10Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2302.14509/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Bohao Qu, Chang Yi, Hechang Chen, Ivor W.Tsang, Jielong Yang, Xiaofeng Cao, Yew-Soon Ong","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-28T11:58:39Z","title":"Policy Dispersion in Non-Markovian Environment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.14509","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:2946fa9141c7b4803683437a8162308483395157529f862a35c29dc3234ca721","target":"record","created_at":"2026-07-05T08:26:10Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"ddf718ff15e61dedcc2690f9eb17d5dad0220cfc8751ffe3455dff03ad2abb0c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-28T11:58:39Z","title_canon_sha256":"709b9e82e17e3d4a263bf80cc3bf5213ad17ba4e625ee275c824f98d86d6fba9"},"schema_version":"1.0","source":{"id":"2302.14509","kind":"arxiv","version":2}},"canonical_sha256":"a85e7d1dc5308b6017866c28754f2aaf3b9a878d41b11221a81d2f8c3867c3a0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a85e7d1dc5308b6017866c28754f2aaf3b9a878d41b11221a81d2f8c3867c3a0","first_computed_at":"2026-07-05T08:26:10.775622Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:26:10.775622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"n7co1/KJbtXwgRMdmAriJ9lDku+GNaMwoCXkRnwT5YRQPge2WSMy5bkEYDydNfOlwQmYUDQH8F5mGFFvAldQCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:26:10.776093Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.14509","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2946fa9141c7b4803683437a8162308483395157529f862a35c29dc3234ca721","sha256:ffec12cfb790506fd05a88f2a2efb09b2083e18e47787bd8c12c413ac60e361c"],"state_sha256":"dbf4b857d401ef25f24e3e655a23e72ff6f3189ca99073e2eec415c89cec3b73"}