{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:NDNTE6MCXWTRADT44BHNZ465AN","short_pith_number":"pith:NDNTE6MC","canonical_record":{"source":{"id":"2405.18795","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-05-29T06:26:52Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6124a2ac898f922fb3beb41cb8ca72a3d462cc4181769a391633f2dab5213741","abstract_canon_sha256":"ff3d2d6785517dea98dd1545bded4ec9528e73bf2e765458cc9f6de7c8b12e73"},"schema_version":"1.0"},"canonical_sha256":"68db327982bda7100e7ce04edcf3dd03585ec7b897b19801e358cf3ecace6d74","source":{"kind":"arxiv","id":"2405.18795","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.18795","created_at":"2026-07-05T10:27:10Z"},{"alias_kind":"arxiv_version","alias_value":"2405.18795v2","created_at":"2026-07-05T10:27:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.18795","created_at":"2026-07-05T10:27:10Z"},{"alias_kind":"pith_short_12","alias_value":"NDNTE6MCXWTR","created_at":"2026-07-05T10:27:10Z"},{"alias_kind":"pith_short_16","alias_value":"NDNTE6MCXWTRADT4","created_at":"2026-07-05T10:27:10Z"},{"alias_kind":"pith_short_8","alias_value":"NDNTE6MC","created_at":"2026-07-05T10:27:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:NDNTE6MCXWTRADT44BHNZ465AN","target":"record","payload":{"canonical_record":{"source":{"id":"2405.18795","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-05-29T06:26:52Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6124a2ac898f922fb3beb41cb8ca72a3d462cc4181769a391633f2dab5213741","abstract_canon_sha256":"ff3d2d6785517dea98dd1545bded4ec9528e73bf2e765458cc9f6de7c8b12e73"},"schema_version":"1.0"},"canonical_sha256":"68db327982bda7100e7ce04edcf3dd03585ec7b897b19801e358cf3ecace6d74","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:27:10.657166Z","signature_b64":"bfTWZEFhUNW1Ph7Hd8VxOZawlImZxoygin7D7gJA2K6pcgJrQ1yyw37lyDy5QUKqXLQwwyMocSZVWfhAqgPtDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"68db327982bda7100e7ce04edcf3dd03585ec7b897b19801e358cf3ecace6d74","last_reissued_at":"2026-07-05T10:27:10.656677Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:27:10.656677Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.18795","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":"2026-07-05T10:27:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tpas8yNCjMnvscxCvt2wZYYRz/7mpUr7AmnD/5ZNJZiYHj+zl33oBhA/vjyLZLkDmLeoepTHppzoGduFcFXKBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T17:39:11.307593Z"},"content_sha256":"70a1a1bd11c76b13ad376a4bf9c76d2b5f6cc02a1cb9d8954a4c0232309edff2","schema_version":"1.0","event_id":"sha256:70a1a1bd11c76b13ad376a4bf9c76d2b5f6cc02a1cb9d8954a4c0232309edff2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:NDNTE6MCXWTRADT44BHNZ465AN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Federated Q-Learning with Reference-Advantage Decomposition: Almost Optimal Regret and Logarithmic Communication Cost","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Haochen Zhang, Lingzhou Xue, Zhong Zheng","submitted_at":"2024-05-29T06:26:52Z","abstract_excerpt":"In this paper, we consider model-free federated reinforcement learning for tabular episodic Markov decision processes. Under the coordination of a central server, multiple agents collaboratively explore the environment and learn an optimal policy without sharing their raw data. Despite recent advances in federated Q-learning algorithms achieving near-linear regret speedup with low communication cost, existing algorithms only attain suboptimal regrets compared to the information bound. We propose a novel model-free federated Q-learning algorithm, termed FedQ-Advantage. Our algorithm leverages r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.18795","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/2405.18795/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":"2026-07-05T10:27:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MjgIjbsMukbXOORBnE4cu90mWZj5i+ANYt6I3L+2utsuJ8NPZMFnbAtkrVdmibRTPc6ucAyKvkPiEI0rZZd4Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T17:39:11.308470Z"},"content_sha256":"d3f704c92f84583d4caec3d95f5ccc6dd296bc5204c5db9dfebb3c8960b751a9","schema_version":"1.0","event_id":"sha256:d3f704c92f84583d4caec3d95f5ccc6dd296bc5204c5db9dfebb3c8960b751a9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NDNTE6MCXWTRADT44BHNZ465AN/bundle.json","state_url":"https://pith.science/pith/NDNTE6MCXWTRADT44BHNZ465AN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NDNTE6MCXWTRADT44BHNZ465AN/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":"2026-08-04T17:39:11Z","links":{"resolver":"https://pith.science/pith/NDNTE6MCXWTRADT44BHNZ465AN","bundle":"https://pith.science/pith/NDNTE6MCXWTRADT44BHNZ465AN/bundle.json","state":"https://pith.science/pith/NDNTE6MCXWTRADT44BHNZ465AN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NDNTE6MCXWTRADT44BHNZ465AN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NDNTE6MCXWTRADT44BHNZ465AN","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":"ff3d2d6785517dea98dd1545bded4ec9528e73bf2e765458cc9f6de7c8b12e73","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-05-29T06:26:52Z","title_canon_sha256":"6124a2ac898f922fb3beb41cb8ca72a3d462cc4181769a391633f2dab5213741"},"schema_version":"1.0","source":{"id":"2405.18795","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.18795","created_at":"2026-07-05T10:27:10Z"},{"alias_kind":"arxiv_version","alias_value":"2405.18795v2","created_at":"2026-07-05T10:27:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.18795","created_at":"2026-07-05T10:27:10Z"},{"alias_kind":"pith_short_12","alias_value":"NDNTE6MCXWTR","created_at":"2026-07-05T10:27:10Z"},{"alias_kind":"pith_short_16","alias_value":"NDNTE6MCXWTRADT4","created_at":"2026-07-05T10:27:10Z"},{"alias_kind":"pith_short_8","alias_value":"NDNTE6MC","created_at":"2026-07-05T10:27:10Z"}],"graph_snapshots":[{"event_id":"sha256:d3f704c92f84583d4caec3d95f5ccc6dd296bc5204c5db9dfebb3c8960b751a9","target":"graph","created_at":"2026-07-05T10:27:10Z","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/2405.18795/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we consider model-free federated reinforcement learning for tabular episodic Markov decision processes. Under the coordination of a central server, multiple agents collaboratively explore the environment and learn an optimal policy without sharing their raw data. Despite recent advances in federated Q-learning algorithms achieving near-linear regret speedup with low communication cost, existing algorithms only attain suboptimal regrets compared to the information bound. We propose a novel model-free federated Q-learning algorithm, termed FedQ-Advantage. Our algorithm leverages r","authors_text":"Haochen Zhang, Lingzhou Xue, Zhong Zheng","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-05-29T06:26:52Z","title":"Federated Q-Learning with Reference-Advantage Decomposition: Almost Optimal Regret and Logarithmic Communication Cost"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.18795","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":"sha256:70a1a1bd11c76b13ad376a4bf9c76d2b5f6cc02a1cb9d8954a4c0232309edff2","target":"record","created_at":"2026-07-05T10:27:10Z","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":"ff3d2d6785517dea98dd1545bded4ec9528e73bf2e765458cc9f6de7c8b12e73","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-05-29T06:26:52Z","title_canon_sha256":"6124a2ac898f922fb3beb41cb8ca72a3d462cc4181769a391633f2dab5213741"},"schema_version":"1.0","source":{"id":"2405.18795","kind":"arxiv","version":2}},"canonical_sha256":"68db327982bda7100e7ce04edcf3dd03585ec7b897b19801e358cf3ecace6d74","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"68db327982bda7100e7ce04edcf3dd03585ec7b897b19801e358cf3ecace6d74","first_computed_at":"2026-07-05T10:27:10.656677Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:27:10.656677Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bfTWZEFhUNW1Ph7Hd8VxOZawlImZxoygin7D7gJA2K6pcgJrQ1yyw37lyDy5QUKqXLQwwyMocSZVWfhAqgPtDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:27:10.657166Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.18795","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:70a1a1bd11c76b13ad376a4bf9c76d2b5f6cc02a1cb9d8954a4c0232309edff2","sha256:d3f704c92f84583d4caec3d95f5ccc6dd296bc5204c5db9dfebb3c8960b751a9"],"state_sha256":"29fec267b58a0339473b385eb55da4904ea5212194152db919e95cf2a024eaef"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hrs9X+0Bhv2145Hoy8stYyWGwizlO4NljeiXLd0MMeGLF69DEFkZL96fPXw54weW3hyDCAO4ZxjxZ8LDmItiAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T17:39:11.314971Z","bundle_sha256":"8b4124f0525199ee6e4e8d8e62c581aea7bb3d268848ea57a6277286f4440800"}}