{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:GUFG4MTQJCUTYJVWHQJ4W6XN6V","short_pith_number":"pith:GUFG4MTQ","schema_version":"1.0","canonical_sha256":"350a6e327048a93c26b63c13cb7aedf542eb26302f031b17deff877d7414d7ca","source":{"kind":"arxiv","id":"2106.03400","version":2},"attestation_state":"computed","paper":{"title":"Believe What You See: Implicit Constraint Approach for Offline Multi-Agent Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chenghao Li, Gao Huang, Jun Yang, Qianchuan Zhao, Qiyuan Zhang, Xiaoteng Ma, Yiqin Yang, Zewu Zheng","submitted_at":"2021-06-07T08:02:31Z","abstract_excerpt":"Learning from datasets without interaction with environments (Offline Learning) is an essential step to apply Reinforcement Learning (RL) algorithms in real-world scenarios. However, compared with the single-agent counterpart, offline multi-agent RL introduces more agents with the larger state and action space, which is more challenging but attracts little attention. We demonstrate current offline RL algorithms are ineffective in multi-agent systems due to the accumulated extrapolation error. In this paper, we propose a novel offline RL algorithm, named Implicit Constraint Q-learning (ICQ), wh"},"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":"2106.03400","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2021-06-07T08:02:31Z","cross_cats_sorted":[],"title_canon_sha256":"a3d2bfcea44d55182e9ce68df03b77417bc370b70a1268c9c4d1313f36340c3f","abstract_canon_sha256":"7e9c166fe89b31571d4051e02497731203405c61a1d170df0489d9776cc57ccb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:25:31.861506Z","signature_b64":"cXZl4rCOQqm4mIpNI20++s8U0wQYjfZE/jo9GWXi+KQ2Xvq+/sd+2F51MraZIkRDO+Dqa+ewiEsSr/5JyTmbAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"350a6e327048a93c26b63c13cb7aedf542eb26302f031b17deff877d7414d7ca","last_reissued_at":"2026-07-05T03:25:31.861045Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:25:31.861045Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Believe What You See: Implicit Constraint Approach for Offline Multi-Agent Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chenghao Li, Gao Huang, Jun Yang, Qianchuan Zhao, Qiyuan Zhang, Xiaoteng Ma, Yiqin Yang, Zewu Zheng","submitted_at":"2021-06-07T08:02:31Z","abstract_excerpt":"Learning from datasets without interaction with environments (Offline Learning) is an essential step to apply Reinforcement Learning (RL) algorithms in real-world scenarios. However, compared with the single-agent counterpart, offline multi-agent RL introduces more agents with the larger state and action space, which is more challenging but attracts little attention. We demonstrate current offline RL algorithms are ineffective in multi-agent systems due to the accumulated extrapolation error. In this paper, we propose a novel offline RL algorithm, named Implicit Constraint Q-learning (ICQ), wh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.03400","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/2106.03400/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":"2106.03400","created_at":"2026-07-05T03:25:31.861106+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.03400v2","created_at":"2026-07-05T03:25:31.861106+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.03400","created_at":"2026-07-05T03:25:31.861106+00:00"},{"alias_kind":"pith_short_12","alias_value":"GUFG4MTQJCUT","created_at":"2026-07-05T03:25:31.861106+00:00"},{"alias_kind":"pith_short_16","alias_value":"GUFG4MTQJCUTYJVW","created_at":"2026-07-05T03:25:31.861106+00:00"},{"alias_kind":"pith_short_8","alias_value":"GUFG4MTQ","created_at":"2026-07-05T03:25:31.861106+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/GUFG4MTQJCUTYJVWHQJ4W6XN6V","json":"https://pith.science/pith/GUFG4MTQJCUTYJVWHQJ4W6XN6V.json","graph_json":"https://pith.science/api/pith-number/GUFG4MTQJCUTYJVWHQJ4W6XN6V/graph.json","events_json":"https://pith.science/api/pith-number/GUFG4MTQJCUTYJVWHQJ4W6XN6V/events.json","paper":"https://pith.science/paper/GUFG4MTQ"},"agent_actions":{"view_html":"https://pith.science/pith/GUFG4MTQJCUTYJVWHQJ4W6XN6V","download_json":"https://pith.science/pith/GUFG4MTQJCUTYJVWHQJ4W6XN6V.json","view_paper":"https://pith.science/paper/GUFG4MTQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.03400&json=true","fetch_graph":"https://pith.science/api/pith-number/GUFG4MTQJCUTYJVWHQJ4W6XN6V/graph.json","fetch_events":"https://pith.science/api/pith-number/GUFG4MTQJCUTYJVWHQJ4W6XN6V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GUFG4MTQJCUTYJVWHQJ4W6XN6V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GUFG4MTQJCUTYJVWHQJ4W6XN6V/action/storage_attestation","attest_author":"https://pith.science/pith/GUFG4MTQJCUTYJVWHQJ4W6XN6V/action/author_attestation","sign_citation":"https://pith.science/pith/GUFG4MTQJCUTYJVWHQJ4W6XN6V/action/citation_signature","submit_replication":"https://pith.science/pith/GUFG4MTQJCUTYJVWHQJ4W6XN6V/action/replication_record"}},"created_at":"2026-07-05T03:25:31.861106+00:00","updated_at":"2026-07-05T03:25:31.861106+00:00"}