{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:2FVU3K2AMPMXA5RS7B4HTTV4UB","short_pith_number":"pith:2FVU3K2A","schema_version":"1.0","canonical_sha256":"d16b4dab4063d9707632f87879cebca04bc2cdc6255544ec6685f4d2850caae8","source":{"kind":"arxiv","id":"2307.01472","version":2},"attestation_state":"computed","paper":{"title":"Improving Generalization and Data Efficiency with Diffusion in Offline Multi-agent RL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.MA"],"primary_cat":"cs.AI","authors_text":"Jiatai Huang, Ling Pan, Longbo Huang, Zhuoran Li","submitted_at":"2023-07-04T04:40:54Z","abstract_excerpt":"We present a novel Diffusion Offline Multi-agent Model (DOM2) for offline Multi-Agent Reinforcement Learning (MARL). Different from existing algorithms that rely mainly on conservatism in policy design, DOM2 enhances policy expressiveness and diversity based on diffusion model. Specifically, we incorporate a diffusion model into the policy network and propose a trajectory-based data-reweighting scheme in training. These key ingredients significantly improve algorithm robustness against environment changes and achieve significant improvements in performance, generalization and data-efficiency. "},"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":"2307.01472","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-07-04T04:40:54Z","cross_cats_sorted":["cs.LG","cs.MA"],"title_canon_sha256":"b2d9982207b13e736eef8530710898e9f135a022e13fa29d0c004446540e95f5","abstract_canon_sha256":"65fe16116269fecf80c8ec9dfba767fdb56b63b7c6de2f4ef896ab2212692dcf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T01:09:07.164971Z","signature_b64":"KQW7aPVaEf1wgRpLeCo1C6eJr9RUItmPFO2FRjZnFTdmwJi2a2ttUCYfQSZvXQPuqi7jJzGsQ3Dc2HKFxvTeCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d16b4dab4063d9707632f87879cebca04bc2cdc6255544ec6685f4d2850caae8","last_reissued_at":"2026-06-11T01:09:07.164037Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T01:09:07.164037Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Generalization and Data Efficiency with Diffusion in Offline Multi-agent RL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.MA"],"primary_cat":"cs.AI","authors_text":"Jiatai Huang, Ling Pan, Longbo Huang, Zhuoran Li","submitted_at":"2023-07-04T04:40:54Z","abstract_excerpt":"We present a novel Diffusion Offline Multi-agent Model (DOM2) for offline Multi-Agent Reinforcement Learning (MARL). Different from existing algorithms that rely mainly on conservatism in policy design, DOM2 enhances policy expressiveness and diversity based on diffusion model. Specifically, we incorporate a diffusion model into the policy network and propose a trajectory-based data-reweighting scheme in training. These key ingredients significantly improve algorithm robustness against environment changes and achieve significant improvements in performance, generalization and data-efficiency. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.01472","kind":"arxiv","version":2},"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/2307.01472/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":"2307.01472","created_at":"2026-06-11T01:09:07.164167+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.01472v2","created_at":"2026-06-11T01:09:07.164167+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.01472","created_at":"2026-06-11T01:09:07.164167+00:00"},{"alias_kind":"pith_short_12","alias_value":"2FVU3K2AMPMX","created_at":"2026-06-11T01:09:07.164167+00:00"},{"alias_kind":"pith_short_16","alias_value":"2FVU3K2AMPMXA5RS","created_at":"2026-06-11T01:09:07.164167+00:00"},{"alias_kind":"pith_short_8","alias_value":"2FVU3K2A","created_at":"2026-06-11T01:09:07.164167+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.07639","citing_title":"Offline Multi-Agent Reinforcement Learning via In-Sample Sequential Policy Optimization","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2FVU3K2AMPMXA5RS7B4HTTV4UB","json":"https://pith.science/pith/2FVU3K2AMPMXA5RS7B4HTTV4UB.json","graph_json":"https://pith.science/api/pith-number/2FVU3K2AMPMXA5RS7B4HTTV4UB/graph.json","events_json":"https://pith.science/api/pith-number/2FVU3K2AMPMXA5RS7B4HTTV4UB/events.json","paper":"https://pith.science/paper/2FVU3K2A"},"agent_actions":{"view_html":"https://pith.science/pith/2FVU3K2AMPMXA5RS7B4HTTV4UB","download_json":"https://pith.science/pith/2FVU3K2AMPMXA5RS7B4HTTV4UB.json","view_paper":"https://pith.science/paper/2FVU3K2A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.01472&json=true","fetch_graph":"https://pith.science/api/pith-number/2FVU3K2AMPMXA5RS7B4HTTV4UB/graph.json","fetch_events":"https://pith.science/api/pith-number/2FVU3K2AMPMXA5RS7B4HTTV4UB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2FVU3K2AMPMXA5RS7B4HTTV4UB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2FVU3K2AMPMXA5RS7B4HTTV4UB/action/storage_attestation","attest_author":"https://pith.science/pith/2FVU3K2AMPMXA5RS7B4HTTV4UB/action/author_attestation","sign_citation":"https://pith.science/pith/2FVU3K2AMPMXA5RS7B4HTTV4UB/action/citation_signature","submit_replication":"https://pith.science/pith/2FVU3K2AMPMXA5RS7B4HTTV4UB/action/replication_record"}},"created_at":"2026-06-11T01:09:07.164167+00:00","updated_at":"2026-06-11T01:09:07.164167+00:00"}