{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:DUTCWG7L4VULOXCNZZ7XKANTJA","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":"fd72c0ec13bf6a68f57b14c33389319e43d640829bd3074328ad9439703f4062","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-22T13:27:42Z","title_canon_sha256":"789f23493e41bbc83bec7d5efc4e48afecc5c0133b0bc1a2024f7ec5acdb2f63"},"schema_version":"1.0","source":{"id":"2111.11188","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.11188","created_at":"2026-07-05T04:11:09Z"},{"alias_kind":"arxiv_version","alias_value":"2111.11188v3","created_at":"2026-07-05T04:11:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.11188","created_at":"2026-07-05T04:11:09Z"},{"alias_kind":"pith_short_12","alias_value":"DUTCWG7L4VUL","created_at":"2026-07-05T04:11:09Z"},{"alias_kind":"pith_short_16","alias_value":"DUTCWG7L4VULOXCN","created_at":"2026-07-05T04:11:09Z"},{"alias_kind":"pith_short_8","alias_value":"DUTCWG7L","created_at":"2026-07-05T04:11:09Z"}],"graph_snapshots":[{"event_id":"sha256:9bf6718a2b30f9573f8e23c2c5b1fb6dd594fab395f2d4672ca1665f02676301","target":"graph","created_at":"2026-07-05T04:11:09Z","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/2111.11188/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Huazhe Xu, Ling Pan, Longbo Huang, Tengyu Ma","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-22T13:27:42Z","title":"Plan Better Amid Conservatism: Offline Multi-Agent Reinforcement Learning with Actor Rectification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.11188","kind":"arxiv","version":3},"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:a65701c178be202780d50a3aa535d49cc158219b133a51f0c6a0ccb1895b579a","target":"record","created_at":"2026-07-05T04:11:09Z","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":"fd72c0ec13bf6a68f57b14c33389319e43d640829bd3074328ad9439703f4062","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-22T13:27:42Z","title_canon_sha256":"789f23493e41bbc83bec7d5efc4e48afecc5c0133b0bc1a2024f7ec5acdb2f63"},"schema_version":"1.0","source":{"id":"2111.11188","kind":"arxiv","version":3}},"canonical_sha256":"1d262b1bebe568b75c4dce7f7501b3481f1fe2d513c099c201fc218c5135d587","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1d262b1bebe568b75c4dce7f7501b3481f1fe2d513c099c201fc218c5135d587","first_computed_at":"2026-07-05T04:11:09.403920Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:11:09.403920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/JbzZiIZgVAUKSNhy/QbjqUkIp5BDV8nUQ7TnL3DQ3RMTVfHJJStxjoGBEtpyX0Sr6DJB7bUrFWXoEs+T37sAw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:11:09.404455Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.11188","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a65701c178be202780d50a3aa535d49cc158219b133a51f0c6a0ccb1895b579a","sha256:9bf6718a2b30f9573f8e23c2c5b1fb6dd594fab395f2d4672ca1665f02676301"],"state_sha256":"7aedf04f72dbc8790e8fb472a0a400e8b60c5788b90fd7efd1850593adaa1df6"}