{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:PW56ZQ23YFN4OPB3RP3SWF4POK","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":"e2693fc3ec9fda04c8ac454b889d316d91f1c8603a45bc5851219a8cd78b43e8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-09-22T08:10:25Z","title_canon_sha256":"be01d8fc15317992c3a7da1a99c2c25615dfefd446fa6099ea09c8afebea27dd"},"schema_version":"1.0","source":{"id":"2309.12696","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.12696","created_at":"2026-07-05T06:53:16Z"},{"alias_kind":"arxiv_version","alias_value":"2309.12696v1","created_at":"2026-07-05T06:53:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.12696","created_at":"2026-07-05T06:53:16Z"},{"alias_kind":"pith_short_12","alias_value":"PW56ZQ23YFN4","created_at":"2026-07-05T06:53:16Z"},{"alias_kind":"pith_short_16","alias_value":"PW56ZQ23YFN4OPB3","created_at":"2026-07-05T06:53:16Z"},{"alias_kind":"pith_short_8","alias_value":"PW56ZQ23","created_at":"2026-07-05T06:53:16Z"}],"graph_snapshots":[{"event_id":"sha256:520adc69f8032812cbfdae34d1772ecb70bb9bb17d6b2acd18bf682257ad93b4","target":"graph","created_at":"2026-07-05T06:53:16Z","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/2309.12696/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline multi-agent reinforcement learning is challenging due to the coupling effect of both distribution shift issue common in offline setting and the high dimension issue common in multi-agent setting, making the action out-of-distribution (OOD) and value overestimation phenomenon excessively severe. Tomitigate this problem, we propose a novel multi-agent offline RL algorithm, named CounterFactual Conservative Q-Learning (CFCQL) to conduct conservative value estimation. Rather than regarding all the agents as a high dimensional single one and directly applying single agent methods to it, CFC","authors_text":"Chen Chen, Hongchang Zhang, Jianzhun Shao, Xiangyang Ji, Yun Qu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-09-22T08:10:25Z","title":"Counterfactual Conservative Q Learning for Offline Multi-agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.12696","kind":"arxiv","version":1},"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":"sha256:55445004b9358a6ae1c7c6b026ad7475256ba24ee0a4b93f1eb7cbd0dd03e796","target":"record","created_at":"2026-07-05T06:53:16Z","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":"e2693fc3ec9fda04c8ac454b889d316d91f1c8603a45bc5851219a8cd78b43e8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-09-22T08:10:25Z","title_canon_sha256":"be01d8fc15317992c3a7da1a99c2c25615dfefd446fa6099ea09c8afebea27dd"},"schema_version":"1.0","source":{"id":"2309.12696","kind":"arxiv","version":1}},"canonical_sha256":"7dbbecc35bc15bc73c3b8bf72b178f72b96ab94dc3066e203c17a4a457cad66b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7dbbecc35bc15bc73c3b8bf72b178f72b96ab94dc3066e203c17a4a457cad66b","first_computed_at":"2026-07-05T06:53:16.359171Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:53:16.359171Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OOI1gQOLjxX1reztnvYibPx0dMpv3Nk6XjrPsbawapSWBbhRj2z+6RUqVYS/jxDqEI9MA2CuBfRK3lDnToB2AA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:53:16.359659Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.12696","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:55445004b9358a6ae1c7c6b026ad7475256ba24ee0a4b93f1eb7cbd0dd03e796","sha256:520adc69f8032812cbfdae34d1772ecb70bb9bb17d6b2acd18bf682257ad93b4"],"state_sha256":"17701d9d3b2bf0de1ff5cc41b1f9870f1c18683ffa6de7214af4c77a40bc74e6"}