{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:VT2OWN4K2R526LPIQAT5Y76ELH","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":"ca3b188367e844ddf7455874b112e9b7696d8363311b7b4e0da480af3f33e312","cross_cats_sorted":["cs.AI","cs.MA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-15T19:13:44Z","title_canon_sha256":"b01131abc014032901df168ec4dd58d1e1c52782887971654b38c876e8c208b6"},"schema_version":"1.0","source":{"id":"2001.07527","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2001.07527","created_at":"2026-07-05T00:34:56Z"},{"alias_kind":"arxiv_version","alias_value":"2001.07527v1","created_at":"2026-07-05T00:34:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.07527","created_at":"2026-07-05T00:34:56Z"},{"alias_kind":"pith_short_12","alias_value":"VT2OWN4K2R52","created_at":"2026-07-05T00:34:56Z"},{"alias_kind":"pith_short_16","alias_value":"VT2OWN4K2R526LPI","created_at":"2026-07-05T00:34:56Z"},{"alias_kind":"pith_short_8","alias_value":"VT2OWN4K","created_at":"2026-07-05T00:34:56Z"}],"graph_snapshots":[{"event_id":"sha256:bb24b6f0ca762a9f93c1ca21382b16a550d15a9ec2dc1bd54a4eff0a4c543558","target":"graph","created_at":"2026-07-05T00:34:56Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2001.07527/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a new model-based reinforcement learning algorithm, Cooperative Prioritized Sweeping, for efficient learning in multi-agent Markov decision processes. The algorithm allows for sample-efficient learning on large problems by exploiting a factorization to approximate the value function. Our approach only requires knowledge about the structure of the problem in the form of a dynamic decision network. Using this information, our method learns a model of the environment and performs temporal difference updates which affect multiple joint states and actions at once. Batch updates are addit","authors_text":"Ann Now\\'e, Diederik M. Roijers, Eugenio Bargiacchi, Timothy Verstraeten","cross_cats":["cs.AI","cs.MA","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-15T19:13:44Z","title":"Model-based Multi-Agent Reinforcement Learning with Cooperative Prioritized Sweeping"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.07527","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":"sha256:54f6b2148baa92b8669d9f263576893b0ebd6873a9a229b5d572d4f983bf893b","target":"record","created_at":"2026-07-05T00:34:56Z","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":"ca3b188367e844ddf7455874b112e9b7696d8363311b7b4e0da480af3f33e312","cross_cats_sorted":["cs.AI","cs.MA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-15T19:13:44Z","title_canon_sha256":"b01131abc014032901df168ec4dd58d1e1c52782887971654b38c876e8c208b6"},"schema_version":"1.0","source":{"id":"2001.07527","kind":"arxiv","version":1}},"canonical_sha256":"acf4eb378ad47baf2de88027dc7fc459e316272b7385d0511436a10cfb514973","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"acf4eb378ad47baf2de88027dc7fc459e316272b7385d0511436a10cfb514973","first_computed_at":"2026-07-05T00:34:56.286020Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:34:56.286020Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hP0epbbf+oz7mcIxocxQj+En2PMduyBUYiksOKl308W8qEDyHlV0c0bX2gJ6lLdyBoqoFMKF7BlGUvGNmwCFAA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:34:56.286482Z","signed_message":"canonical_sha256_bytes"},"source_id":"2001.07527","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:54f6b2148baa92b8669d9f263576893b0ebd6873a9a229b5d572d4f983bf893b","sha256:bb24b6f0ca762a9f93c1ca21382b16a550d15a9ec2dc1bd54a4eff0a4c543558"],"state_sha256":"880caf68a60fc2f1ee445ca3f00c82712c769111564064c7ed7e32abdb4c8838"}