{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:VT2OWN4K2R526LPIQAT5Y76ELH","short_pith_number":"pith:VT2OWN4K","schema_version":"1.0","canonical_sha256":"acf4eb378ad47baf2de88027dc7fc459e316272b7385d0511436a10cfb514973","source":{"kind":"arxiv","id":"2001.07527","version":1},"attestation_state":"computed","paper":{"title":"Model-based Multi-Agent Reinforcement Learning with Cooperative Prioritized Sweeping","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ann Now\\'e, Diederik M. Roijers, Eugenio Bargiacchi, Timothy Verstraeten","submitted_at":"2020-01-15T19:13:44Z","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"},"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":"2001.07527","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-15T19:13:44Z","cross_cats_sorted":["cs.AI","cs.MA","stat.ML"],"title_canon_sha256":"b01131abc014032901df168ec4dd58d1e1c52782887971654b38c876e8c208b6","abstract_canon_sha256":"ca3b188367e844ddf7455874b112e9b7696d8363311b7b4e0da480af3f33e312"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:34:56.286482Z","signature_b64":"hP0epbbf+oz7mcIxocxQj+En2PMduyBUYiksOKl308W8qEDyHlV0c0bX2gJ6lLdyBoqoFMKF7BlGUvGNmwCFAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"acf4eb378ad47baf2de88027dc7fc459e316272b7385d0511436a10cfb514973","last_reissued_at":"2026-07-05T00:34:56.286020Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:34:56.286020Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Model-based Multi-Agent Reinforcement Learning with Cooperative Prioritized Sweeping","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ann Now\\'e, Diederik M. Roijers, Eugenio Bargiacchi, Timothy Verstraeten","submitted_at":"2020-01-15T19:13:44Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.07527","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2001.07527/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2001.07527","created_at":"2026-07-05T00:34:56.286076+00:00"},{"alias_kind":"arxiv_version","alias_value":"2001.07527v1","created_at":"2026-07-05T00:34:56.286076+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.07527","created_at":"2026-07-05T00:34:56.286076+00:00"},{"alias_kind":"pith_short_12","alias_value":"VT2OWN4K2R52","created_at":"2026-07-05T00:34:56.286076+00:00"},{"alias_kind":"pith_short_16","alias_value":"VT2OWN4K2R526LPI","created_at":"2026-07-05T00:34:56.286076+00:00"},{"alias_kind":"pith_short_8","alias_value":"VT2OWN4K","created_at":"2026-07-05T00:34:56.286076+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/VT2OWN4K2R526LPIQAT5Y76ELH","json":"https://pith.science/pith/VT2OWN4K2R526LPIQAT5Y76ELH.json","graph_json":"https://pith.science/api/pith-number/VT2OWN4K2R526LPIQAT5Y76ELH/graph.json","events_json":"https://pith.science/api/pith-number/VT2OWN4K2R526LPIQAT5Y76ELH/events.json","paper":"https://pith.science/paper/VT2OWN4K"},"agent_actions":{"view_html":"https://pith.science/pith/VT2OWN4K2R526LPIQAT5Y76ELH","download_json":"https://pith.science/pith/VT2OWN4K2R526LPIQAT5Y76ELH.json","view_paper":"https://pith.science/paper/VT2OWN4K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2001.07527&json=true","fetch_graph":"https://pith.science/api/pith-number/VT2OWN4K2R526LPIQAT5Y76ELH/graph.json","fetch_events":"https://pith.science/api/pith-number/VT2OWN4K2R526LPIQAT5Y76ELH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VT2OWN4K2R526LPIQAT5Y76ELH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VT2OWN4K2R526LPIQAT5Y76ELH/action/storage_attestation","attest_author":"https://pith.science/pith/VT2OWN4K2R526LPIQAT5Y76ELH/action/author_attestation","sign_citation":"https://pith.science/pith/VT2OWN4K2R526LPIQAT5Y76ELH/action/citation_signature","submit_replication":"https://pith.science/pith/VT2OWN4K2R526LPIQAT5Y76ELH/action/replication_record"}},"created_at":"2026-07-05T00:34:56.286076+00:00","updated_at":"2026-07-05T00:34:56.286076+00:00"}