{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:DUTCWG7L4VULOXCNZZ7XKANTJA","short_pith_number":"pith:DUTCWG7L","schema_version":"1.0","canonical_sha256":"1d262b1bebe568b75c4dce7f7501b3481f1fe2d513c099c201fc218c5135d587","source":{"kind":"arxiv","id":"2111.11188","version":3},"attestation_state":"computed","paper":{"title":"Plan Better Amid Conservatism: Offline Multi-Agent Reinforcement Learning with Actor Rectification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Huazhe Xu, Ling Pan, Longbo Huang, Tengyu Ma","submitted_at":"2021-11-22T13:27:42Z","abstract_excerpt":"Conservatism has led to significant progress in offline reinforcement learning (RL) where an agent learns from pre-collected datasets. However, as many real-world scenarios involve interaction among multiple agents, it is important to resolve offline RL in the multi-agent setting. Given the recent success of transferring online RL algorithms to the multi-agent setting, one may expect that offline RL algorithms will also transfer to multi-agent settings directly. Surprisingly, we empirically observe that conservative offline RL algorithms do not work well in the multi-agent setting -- the perfo"},"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":"2111.11188","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-22T13:27:42Z","cross_cats_sorted":[],"title_canon_sha256":"789f23493e41bbc83bec7d5efc4e48afecc5c0133b0bc1a2024f7ec5acdb2f63","abstract_canon_sha256":"fd72c0ec13bf6a68f57b14c33389319e43d640829bd3074328ad9439703f4062"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:11:09.404455Z","signature_b64":"/JbzZiIZgVAUKSNhy/QbjqUkIp5BDV8nUQ7TnL3DQ3RMTVfHJJStxjoGBEtpyX0Sr6DJB7bUrFWXoEs+T37sAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d262b1bebe568b75c4dce7f7501b3481f1fe2d513c099c201fc218c5135d587","last_reissued_at":"2026-07-05T04:11:09.403920Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:11:09.403920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Plan Better Amid Conservatism: Offline Multi-Agent Reinforcement Learning with Actor Rectification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Huazhe Xu, Ling Pan, Longbo Huang, Tengyu Ma","submitted_at":"2021-11-22T13:27:42Z","abstract_excerpt":"Conservatism has led to significant progress in offline reinforcement learning (RL) where an agent learns from pre-collected datasets. However, as many real-world scenarios involve interaction among multiple agents, it is important to resolve offline RL in the multi-agent setting. Given the recent success of transferring online RL algorithms to the multi-agent setting, one may expect that offline RL algorithms will also transfer to multi-agent settings directly. Surprisingly, we empirically observe that conservative offline RL algorithms do not work well in the multi-agent setting -- the perfo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.11188","kind":"arxiv","version":3},"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/2111.11188/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":"2111.11188","created_at":"2026-07-05T04:11:09.404064+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.11188v3","created_at":"2026-07-05T04:11:09.404064+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.11188","created_at":"2026-07-05T04:11:09.404064+00:00"},{"alias_kind":"pith_short_12","alias_value":"DUTCWG7L4VUL","created_at":"2026-07-05T04:11:09.404064+00:00"},{"alias_kind":"pith_short_16","alias_value":"DUTCWG7L4VULOXCN","created_at":"2026-07-05T04:11:09.404064+00:00"},{"alias_kind":"pith_short_8","alias_value":"DUTCWG7L","created_at":"2026-07-05T04:11:09.404064+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12640","citing_title":"Individual Control Barrier Functions-Guided Diffusion Model for Safe Offline Multi-Agent Reinforcement Learning","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DUTCWG7L4VULOXCNZZ7XKANTJA","json":"https://pith.science/pith/DUTCWG7L4VULOXCNZZ7XKANTJA.json","graph_json":"https://pith.science/api/pith-number/DUTCWG7L4VULOXCNZZ7XKANTJA/graph.json","events_json":"https://pith.science/api/pith-number/DUTCWG7L4VULOXCNZZ7XKANTJA/events.json","paper":"https://pith.science/paper/DUTCWG7L"},"agent_actions":{"view_html":"https://pith.science/pith/DUTCWG7L4VULOXCNZZ7XKANTJA","download_json":"https://pith.science/pith/DUTCWG7L4VULOXCNZZ7XKANTJA.json","view_paper":"https://pith.science/paper/DUTCWG7L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.11188&json=true","fetch_graph":"https://pith.science/api/pith-number/DUTCWG7L4VULOXCNZZ7XKANTJA/graph.json","fetch_events":"https://pith.science/api/pith-number/DUTCWG7L4VULOXCNZZ7XKANTJA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DUTCWG7L4VULOXCNZZ7XKANTJA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DUTCWG7L4VULOXCNZZ7XKANTJA/action/storage_attestation","attest_author":"https://pith.science/pith/DUTCWG7L4VULOXCNZZ7XKANTJA/action/author_attestation","sign_citation":"https://pith.science/pith/DUTCWG7L4VULOXCNZZ7XKANTJA/action/citation_signature","submit_replication":"https://pith.science/pith/DUTCWG7L4VULOXCNZZ7XKANTJA/action/replication_record"}},"created_at":"2026-07-05T04:11:09.404064+00:00","updated_at":"2026-07-05T04:11:09.404064+00:00"}