{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:GUFG4MTQJCUTYJVWHQJ4W6XN6V","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":"7e9c166fe89b31571d4051e02497731203405c61a1d170df0489d9776cc57ccb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2021-06-07T08:02:31Z","title_canon_sha256":"a3d2bfcea44d55182e9ce68df03b77417bc370b70a1268c9c4d1313f36340c3f"},"schema_version":"1.0","source":{"id":"2106.03400","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.03400","created_at":"2026-07-05T03:25:31Z"},{"alias_kind":"arxiv_version","alias_value":"2106.03400v2","created_at":"2026-07-05T03:25:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.03400","created_at":"2026-07-05T03:25:31Z"},{"alias_kind":"pith_short_12","alias_value":"GUFG4MTQJCUT","created_at":"2026-07-05T03:25:31Z"},{"alias_kind":"pith_short_16","alias_value":"GUFG4MTQJCUTYJVW","created_at":"2026-07-05T03:25:31Z"},{"alias_kind":"pith_short_8","alias_value":"GUFG4MTQ","created_at":"2026-07-05T03:25:31Z"}],"graph_snapshots":[{"event_id":"sha256:2e0078c0282a4069f4061ec171f299d918d265978f0fb5c754f627ce5d093bb2","target":"graph","created_at":"2026-07-05T03:25:31Z","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/2106.03400/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chenghao Li, Gao Huang, Jun Yang, Qianchuan Zhao, Qiyuan Zhang, Xiaoteng Ma, Yiqin Yang, Zewu Zheng","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2021-06-07T08:02:31Z","title":"Believe What You See: Implicit Constraint Approach for Offline Multi-Agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.03400","kind":"arxiv","version":2},"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:c2a2ae85901d044bc374c34a43d0008ede8a490546e4e328cc7ce4316c117168","target":"record","created_at":"2026-07-05T03:25:31Z","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":"7e9c166fe89b31571d4051e02497731203405c61a1d170df0489d9776cc57ccb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2021-06-07T08:02:31Z","title_canon_sha256":"a3d2bfcea44d55182e9ce68df03b77417bc370b70a1268c9c4d1313f36340c3f"},"schema_version":"1.0","source":{"id":"2106.03400","kind":"arxiv","version":2}},"canonical_sha256":"350a6e327048a93c26b63c13cb7aedf542eb26302f031b17deff877d7414d7ca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"350a6e327048a93c26b63c13cb7aedf542eb26302f031b17deff877d7414d7ca","first_computed_at":"2026-07-05T03:25:31.861045Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:25:31.861045Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cXZl4rCOQqm4mIpNI20++s8U0wQYjfZE/jo9GWXi+KQ2Xvq+/sd+2F51MraZIkRDO+Dqa+ewiEsSr/5JyTmbAg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:25:31.861506Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.03400","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c2a2ae85901d044bc374c34a43d0008ede8a490546e4e328cc7ce4316c117168","sha256:2e0078c0282a4069f4061ec171f299d918d265978f0fb5c754f627ce5d093bb2"],"state_sha256":"31515995da9e36ff7b84bcb2c9b035bbbd13ab6d6f35f7f40fd87fd8a8cd9f10"}