{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:ZVQZI7YSXXODFQVFWK7BAFG3NJ","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":"8ef6b3e49b0eb893209dbf8732cb4396c43a116235176a20f2ecc8b2da68d3b3","cross_cats_sorted":["cs.AI","cs.LG","cs.MA","cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2020-05-04T16:34:24Z","title_canon_sha256":"4727ef081d32dddccd2f9eb65265f4f6f608923dc6941a0f6dd19da5987f33ad"},"schema_version":"1.0","source":{"id":"2005.01627","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.01627","created_at":"2026-07-05T01:00:09Z"},{"alias_kind":"arxiv_version","alias_value":"2005.01627v1","created_at":"2026-07-05T01:00:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.01627","created_at":"2026-07-05T01:00:09Z"},{"alias_kind":"pith_short_12","alias_value":"ZVQZI7YSXXOD","created_at":"2026-07-05T01:00:09Z"},{"alias_kind":"pith_short_16","alias_value":"ZVQZI7YSXXODFQVF","created_at":"2026-07-05T01:00:09Z"},{"alias_kind":"pith_short_8","alias_value":"ZVQZI7YS","created_at":"2026-07-05T01:00:09Z"}],"graph_snapshots":[{"event_id":"sha256:c24fd7093cb2844150f55b3eebacce089c4699cd7a0a6eef9f413f45b30e7def","target":"graph","created_at":"2026-07-05T01:00:09Z","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/2005.01627/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider infinite horizon dynamic programming problems, where the control at each stage consists of several distinct decisions, each one made by one of several agents. In an earlier work we introduced a policy iteration algorithm, where the policy improvement is done one-agent-at-a-time in a given order, with knowledge of the choices of the preceding agents in the order. As a result, the amount of computation for each policy improvement grows linearly with the number of agents, as opposed to exponentially for the standard all-agents-at-once method. For the case of a finite-state discounted ","authors_text":"Dimitri Bertsekas","cross_cats":["cs.AI","cs.LG","cs.MA","cs.SY","eess.SY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2020-05-04T16:34:24Z","title":"Multiagent Value Iteration Algorithms in Dynamic Programming and Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.01627","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":"sha256:86872e0fb4f488963d9bc95aaa5f3caa537eced605305cce0ef110c9cde73d98","target":"record","created_at":"2026-07-05T01:00:09Z","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":"8ef6b3e49b0eb893209dbf8732cb4396c43a116235176a20f2ecc8b2da68d3b3","cross_cats_sorted":["cs.AI","cs.LG","cs.MA","cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2020-05-04T16:34:24Z","title_canon_sha256":"4727ef081d32dddccd2f9eb65265f4f6f608923dc6941a0f6dd19da5987f33ad"},"schema_version":"1.0","source":{"id":"2005.01627","kind":"arxiv","version":1}},"canonical_sha256":"cd61947f12bddc32c2a5b2be1014db6a7dd96060e08de7404cd391c965497e10","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cd61947f12bddc32c2a5b2be1014db6a7dd96060e08de7404cd391c965497e10","first_computed_at":"2026-07-05T01:00:09.628694Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:00:09.628694Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JZ+Vl1X6o39E2gM1id6HW+6ZtoN1FfWajzDpGHTvKQ4fBSE62txCRGHWk6tSo6djH6t/HuNuUDTZabCp1TMJBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:00:09.629181Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.01627","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:86872e0fb4f488963d9bc95aaa5f3caa537eced605305cce0ef110c9cde73d98","sha256:c24fd7093cb2844150f55b3eebacce089c4699cd7a0a6eef9f413f45b30e7def"],"state_sha256":"7f2f0ca5075a73dc3bd9da359020d7bae0c400988b8de2b6ab0550e1b191c31c"}