{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:JZ5ONMED3FUYNEYKV4TB32BNJE","short_pith_number":"pith:JZ5ONMED","canonical_record":{"source":{"id":"2108.01832","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-08-04T03:53:33Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"2f352491787acff2d7cdc954325aac707e44bb71712613659ca330bcb4ebe015","abstract_canon_sha256":"c942a37202f47e4d4d2f08931be63767981d1ef766c24fa770e51f5ea64ff7f6"},"schema_version":"1.0"},"canonical_sha256":"4e7ae6b083d96986930aaf261de82d4922527c0d382b305a806a6fbb575b0844","source":{"kind":"arxiv","id":"2108.01832","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.01832","created_at":"2026-07-05T06:35:42Z"},{"alias_kind":"arxiv_version","alias_value":"2108.01832v2","created_at":"2026-07-05T06:35:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.01832","created_at":"2026-07-05T06:35:42Z"},{"alias_kind":"pith_short_12","alias_value":"JZ5ONMED3FUY","created_at":"2026-07-05T06:35:42Z"},{"alias_kind":"pith_short_16","alias_value":"JZ5ONMED3FUYNEYK","created_at":"2026-07-05T06:35:42Z"},{"alias_kind":"pith_short_8","alias_value":"JZ5ONMED","created_at":"2026-07-05T06:35:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:JZ5ONMED3FUYNEYKV4TB32BNJE","target":"record","payload":{"canonical_record":{"source":{"id":"2108.01832","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-08-04T03:53:33Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"2f352491787acff2d7cdc954325aac707e44bb71712613659ca330bcb4ebe015","abstract_canon_sha256":"c942a37202f47e4d4d2f08931be63767981d1ef766c24fa770e51f5ea64ff7f6"},"schema_version":"1.0"},"canonical_sha256":"4e7ae6b083d96986930aaf261de82d4922527c0d382b305a806a6fbb575b0844","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:35:42.212779Z","signature_b64":"b93tKcxH7y64jTI/mxARwxuaPVcckYEORFHc2m8dsv4yNtqQu4VKwRe5FjTOX8DvuC5u6wPhVt/MBminnt9yDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4e7ae6b083d96986930aaf261de82d4922527c0d382b305a806a6fbb575b0844","last_reissued_at":"2026-07-05T06:35:42.212256Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:35:42.212256Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2108.01832","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:35:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oPI45SHWxw9KXsZB3TKDs3SzcAyiziIpdXr/oO7nu3JluEE1kkcXDR3hApz5XQgtlBnQ0mVpbulsa6v+SvgMCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T16:32:04.757890Z"},"content_sha256":"dcdcb5b69e2526105d8a8b6dc4add0ddb3e320c9076be2b8f1833afc95ab5ed1","schema_version":"1.0","event_id":"sha256:dcdcb5b69e2526105d8a8b6dc4add0ddb3e320c9076be2b8f1833afc95ab5ed1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:JZ5ONMED3FUYNEYKV4TB32BNJE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Offline Decentralized Multi-Agent Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.LG","authors_text":"Jiechuan Jiang, Zongqing Lu","submitted_at":"2021-08-04T03:53:33Z","abstract_excerpt":"In many real-world multi-agent cooperative tasks, due to high cost and risk, agents cannot continuously interact with the environment and collect experiences during learning, but have to learn from offline datasets. However, the transition dynamics in the dataset of each agent can be much different from the ones induced by the learned policies of other agents in execution, creating large errors in value estimates. Consequently, agents learn uncoordinated low-performing policies. In this paper, we propose a framework for offline decentralized multi-agent reinforcement learning, which exploits v"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.01832","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/2108.01832/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:35:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q1um1pKKWDZMidcfcQqTVYF39vnxlbGCqK/Fa+ZvrS+X9uCxp/7RKtVDWigfAJazjJGL75Dca/t4M1d2SJnLCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T16:32:04.758778Z"},"content_sha256":"ade909ef1397ceaebc0682a0fee0259a42e4f0f9e7b759da157eec74458cc9c6","schema_version":"1.0","event_id":"sha256:ade909ef1397ceaebc0682a0fee0259a42e4f0f9e7b759da157eec74458cc9c6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JZ5ONMED3FUYNEYKV4TB32BNJE/bundle.json","state_url":"https://pith.science/pith/JZ5ONMED3FUYNEYKV4TB32BNJE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JZ5ONMED3FUYNEYKV4TB32BNJE/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-17T16:32:04Z","links":{"resolver":"https://pith.science/pith/JZ5ONMED3FUYNEYKV4TB32BNJE","bundle":"https://pith.science/pith/JZ5ONMED3FUYNEYKV4TB32BNJE/bundle.json","state":"https://pith.science/pith/JZ5ONMED3FUYNEYKV4TB32BNJE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JZ5ONMED3FUYNEYKV4TB32BNJE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:JZ5ONMED3FUYNEYKV4TB32BNJE","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":"c942a37202f47e4d4d2f08931be63767981d1ef766c24fa770e51f5ea64ff7f6","cross_cats_sorted":["cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-08-04T03:53:33Z","title_canon_sha256":"2f352491787acff2d7cdc954325aac707e44bb71712613659ca330bcb4ebe015"},"schema_version":"1.0","source":{"id":"2108.01832","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.01832","created_at":"2026-07-05T06:35:42Z"},{"alias_kind":"arxiv_version","alias_value":"2108.01832v2","created_at":"2026-07-05T06:35:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.01832","created_at":"2026-07-05T06:35:42Z"},{"alias_kind":"pith_short_12","alias_value":"JZ5ONMED3FUY","created_at":"2026-07-05T06:35:42Z"},{"alias_kind":"pith_short_16","alias_value":"JZ5ONMED3FUYNEYK","created_at":"2026-07-05T06:35:42Z"},{"alias_kind":"pith_short_8","alias_value":"JZ5ONMED","created_at":"2026-07-05T06:35:42Z"}],"graph_snapshots":[{"event_id":"sha256:ade909ef1397ceaebc0682a0fee0259a42e4f0f9e7b759da157eec74458cc9c6","target":"graph","created_at":"2026-07-05T06:35:42Z","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/2108.01832/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In many real-world multi-agent cooperative tasks, due to high cost and risk, agents cannot continuously interact with the environment and collect experiences during learning, but have to learn from offline datasets. However, the transition dynamics in the dataset of each agent can be much different from the ones induced by the learned policies of other agents in execution, creating large errors in value estimates. Consequently, agents learn uncoordinated low-performing policies. In this paper, we propose a framework for offline decentralized multi-agent reinforcement learning, which exploits v","authors_text":"Jiechuan Jiang, Zongqing Lu","cross_cats":["cs.MA"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-08-04T03:53:33Z","title":"Offline Decentralized Multi-Agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.01832","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:dcdcb5b69e2526105d8a8b6dc4add0ddb3e320c9076be2b8f1833afc95ab5ed1","target":"record","created_at":"2026-07-05T06:35:42Z","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":"c942a37202f47e4d4d2f08931be63767981d1ef766c24fa770e51f5ea64ff7f6","cross_cats_sorted":["cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-08-04T03:53:33Z","title_canon_sha256":"2f352491787acff2d7cdc954325aac707e44bb71712613659ca330bcb4ebe015"},"schema_version":"1.0","source":{"id":"2108.01832","kind":"arxiv","version":2}},"canonical_sha256":"4e7ae6b083d96986930aaf261de82d4922527c0d382b305a806a6fbb575b0844","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4e7ae6b083d96986930aaf261de82d4922527c0d382b305a806a6fbb575b0844","first_computed_at":"2026-07-05T06:35:42.212256Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:35:42.212256Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"b93tKcxH7y64jTI/mxARwxuaPVcckYEORFHc2m8dsv4yNtqQu4VKwRe5FjTOX8DvuC5u6wPhVt/MBminnt9yDg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:35:42.212779Z","signed_message":"canonical_sha256_bytes"},"source_id":"2108.01832","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dcdcb5b69e2526105d8a8b6dc4add0ddb3e320c9076be2b8f1833afc95ab5ed1","sha256:ade909ef1397ceaebc0682a0fee0259a42e4f0f9e7b759da157eec74458cc9c6"],"state_sha256":"041afde390c5977695afc77fa4a7183772f6bc4cfd64f967fc6a4971226f5a48"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OvwUGvSb6tV5RCNFxzGutEGN2CgQu5+q+4jmLI2KL/+DC29KFCn69VtwLQXRJpUy7sSMhjDA835XGqu7+NCkAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T16:32:04.773825Z","bundle_sha256":"cb7688abae492dcf16d3e86d265aab18b4d68677de447423fa91b39c3f8d229c"}}