{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:5P4OVRHQEPM74PYXZKT2A5WRDY","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":"96545ff15c5737966049d41b84a594ab16b3ab5c21c272f4daac75902e754472","cross_cats_sorted":["cs.LG","cs.MA","cs.NE","cs.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-04-09T09:45:29Z","title_canon_sha256":"08463e4985579ddf53a332547f1b87411daf902383b7367bcba1a3608cd636ec"},"schema_version":"1.0","source":{"id":"1804.02884","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.02884","created_at":"2026-05-18T00:18:56Z"},{"alias_kind":"arxiv_version","alias_value":"1804.02884v1","created_at":"2026-05-18T00:18:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.02884","created_at":"2026-05-18T00:18:56Z"},{"alias_kind":"pith_short_12","alias_value":"5P4OVRHQEPM7","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"5P4OVRHQEPM74PYX","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"5P4OVRHQ","created_at":"2026-05-18T12:32:08Z"}],"graph_snapshots":[{"event_id":"sha256:39d06730837db0722d1cdddf7a480884d2ca12c8a84092590536cff7f9c71a78","target":"graph","created_at":"2026-05-18T00:18:56Z","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"},"paper":{"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","authors_text":"Akshat Kumar, Duc Thien Nguyen, Hoong Chuin LAU","cross_cats":["cs.LG","cs.MA","cs.NE","cs.SY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-04-09T09:45:29Z","title":"Policy Gradient With Value Function Approximation For Collective Multiagent Planning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.02884","kind":"arxiv","version":1},"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:eeee35732632f248fd79678e163eeea19a1c7d2ecb94a969d1635ddd97848994","target":"record","created_at":"2026-05-18T00:18:56Z","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":"96545ff15c5737966049d41b84a594ab16b3ab5c21c272f4daac75902e754472","cross_cats_sorted":["cs.LG","cs.MA","cs.NE","cs.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-04-09T09:45:29Z","title_canon_sha256":"08463e4985579ddf53a332547f1b87411daf902383b7367bcba1a3608cd636ec"},"schema_version":"1.0","source":{"id":"1804.02884","kind":"arxiv","version":1}},"canonical_sha256":"ebf8eac4f023d9fe3f17caa7a076d11e121d0f2d61fe7b260f5c1bb6d00223fb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ebf8eac4f023d9fe3f17caa7a076d11e121d0f2d61fe7b260f5c1bb6d00223fb","first_computed_at":"2026-05-18T00:18:56.840226Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:18:56.840226Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"U557SSoVM12+qcwWhK2wLZZtJolfqL36TDk1cBXV+cXFLXdNfFWBBytb/r/QpjLusgXb8G0w6b+JuvVloulBBw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:18:56.840630Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.02884","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eeee35732632f248fd79678e163eeea19a1c7d2ecb94a969d1635ddd97848994","sha256:39d06730837db0722d1cdddf7a480884d2ca12c8a84092590536cff7f9c71a78"],"state_sha256":"7c1c25f76f932da94f3a5715433c6e886b4d19f86b0acddd0493067c631a23a5"}