{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:5P4OVRHQEPM74PYXZKT2A5WRDY","short_pith_number":"pith:5P4OVRHQ","schema_version":"1.0","canonical_sha256":"ebf8eac4f023d9fe3f17caa7a076d11e121d0f2d61fe7b260f5c1bb6d00223fb","source":{"kind":"arxiv","id":"1804.02884","version":1},"attestation_state":"computed","paper":{"title":"Policy Gradient With Value Function Approximation For Collective Multiagent Planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.MA","cs.NE","cs.SY"],"primary_cat":"cs.AI","authors_text":"Akshat Kumar, Duc Thien Nguyen, Hoong Chuin LAU","submitted_at":"2018-04-09T09:45:29Z","abstract_excerpt":"Decentralized (PO)MDPs provide an expressive framework for sequential decision making in a multiagent system. Given their computational complexity, recent research has focused on tractable yet practical subclasses of Dec-POMDPs. We address such a subclass called CDEC-POMDP where the collective behavior of a population of agents affects the joint-reward and environment dynamics. Our main contribution is an actor-critic (AC) reinforcement learning method for optimizing CDEC-POMDP policies. Vanilla AC has slow convergence for larger problems. To address this, we show how a particular decompositio"},"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":"1804.02884","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-04-09T09:45:29Z","cross_cats_sorted":["cs.LG","cs.MA","cs.NE","cs.SY"],"title_canon_sha256":"08463e4985579ddf53a332547f1b87411daf902383b7367bcba1a3608cd636ec","abstract_canon_sha256":"96545ff15c5737966049d41b84a594ab16b3ab5c21c272f4daac75902e754472"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:18:56.840630Z","signature_b64":"U557SSoVM12+qcwWhK2wLZZtJolfqL36TDk1cBXV+cXFLXdNfFWBBytb/r/QpjLusgXb8G0w6b+JuvVloulBBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ebf8eac4f023d9fe3f17caa7a076d11e121d0f2d61fe7b260f5c1bb6d00223fb","last_reissued_at":"2026-05-18T00:18:56.840226Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:18:56.840226Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Policy Gradient With Value Function Approximation For Collective Multiagent Planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.MA","cs.NE","cs.SY"],"primary_cat":"cs.AI","authors_text":"Akshat Kumar, Duc Thien Nguyen, Hoong Chuin LAU","submitted_at":"2018-04-09T09:45:29Z","abstract_excerpt":"Decentralized (PO)MDPs provide an expressive framework for sequential decision making in a multiagent system. Given their computational complexity, recent research has focused on tractable yet practical subclasses of Dec-POMDPs. We address such a subclass called CDEC-POMDP where the collective behavior of a population of agents affects the joint-reward and environment dynamics. Our main contribution is an actor-critic (AC) reinforcement learning method for optimizing CDEC-POMDP policies. Vanilla AC has slow convergence for larger problems. To address this, we show how a particular decompositio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.02884","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":""},"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":"1804.02884","created_at":"2026-05-18T00:18:56.840295+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.02884v1","created_at":"2026-05-18T00:18:56.840295+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.02884","created_at":"2026-05-18T00:18:56.840295+00:00"},{"alias_kind":"pith_short_12","alias_value":"5P4OVRHQEPM7","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_16","alias_value":"5P4OVRHQEPM74PYX","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_8","alias_value":"5P4OVRHQ","created_at":"2026-05-18T12:32:08.215937+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/5P4OVRHQEPM74PYXZKT2A5WRDY","json":"https://pith.science/pith/5P4OVRHQEPM74PYXZKT2A5WRDY.json","graph_json":"https://pith.science/api/pith-number/5P4OVRHQEPM74PYXZKT2A5WRDY/graph.json","events_json":"https://pith.science/api/pith-number/5P4OVRHQEPM74PYXZKT2A5WRDY/events.json","paper":"https://pith.science/paper/5P4OVRHQ"},"agent_actions":{"view_html":"https://pith.science/pith/5P4OVRHQEPM74PYXZKT2A5WRDY","download_json":"https://pith.science/pith/5P4OVRHQEPM74PYXZKT2A5WRDY.json","view_paper":"https://pith.science/paper/5P4OVRHQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.02884&json=true","fetch_graph":"https://pith.science/api/pith-number/5P4OVRHQEPM74PYXZKT2A5WRDY/graph.json","fetch_events":"https://pith.science/api/pith-number/5P4OVRHQEPM74PYXZKT2A5WRDY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5P4OVRHQEPM74PYXZKT2A5WRDY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5P4OVRHQEPM74PYXZKT2A5WRDY/action/storage_attestation","attest_author":"https://pith.science/pith/5P4OVRHQEPM74PYXZKT2A5WRDY/action/author_attestation","sign_citation":"https://pith.science/pith/5P4OVRHQEPM74PYXZKT2A5WRDY/action/citation_signature","submit_replication":"https://pith.science/pith/5P4OVRHQEPM74PYXZKT2A5WRDY/action/replication_record"}},"created_at":"2026-05-18T00:18:56.840295+00:00","updated_at":"2026-05-18T00:18:56.840295+00:00"}