{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:XNCJH2JN3N5MOYQZQYD4LTXEMY","short_pith_number":"pith:XNCJH2JN","canonical_record":{"source":{"id":"2405.19499","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-29T20:24:42Z","cross_cats_sorted":["cs.MA","math.OC"],"title_canon_sha256":"5a7b3d72f4ffd39c80867b7b6de296df4c5e3db51e57c135697c590da1e7b0d9","abstract_canon_sha256":"9c6176dedaa47780d8e6714e0bb6a75d60700a5a2f6cc04192ed858970052d36"},"schema_version":"1.0"},"canonical_sha256":"bb4493e92ddb7ac762198607c5cee46620693112c2fdd69e84aab16dd468464e","source":{"kind":"arxiv","id":"2405.19499","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.19499","created_at":"2026-07-05T08:25:35Z"},{"alias_kind":"arxiv_version","alias_value":"2405.19499v1","created_at":"2026-07-05T08:25:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.19499","created_at":"2026-07-05T08:25:35Z"},{"alias_kind":"pith_short_12","alias_value":"XNCJH2JN3N5M","created_at":"2026-07-05T08:25:35Z"},{"alias_kind":"pith_short_16","alias_value":"XNCJH2JN3N5MOYQZ","created_at":"2026-07-05T08:25:35Z"},{"alias_kind":"pith_short_8","alias_value":"XNCJH2JN","created_at":"2026-07-05T08:25:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:XNCJH2JN3N5MOYQZQYD4LTXEMY","target":"record","payload":{"canonical_record":{"source":{"id":"2405.19499","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-29T20:24:42Z","cross_cats_sorted":["cs.MA","math.OC"],"title_canon_sha256":"5a7b3d72f4ffd39c80867b7b6de296df4c5e3db51e57c135697c590da1e7b0d9","abstract_canon_sha256":"9c6176dedaa47780d8e6714e0bb6a75d60700a5a2f6cc04192ed858970052d36"},"schema_version":"1.0"},"canonical_sha256":"bb4493e92ddb7ac762198607c5cee46620693112c2fdd69e84aab16dd468464e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:25:35.341174Z","signature_b64":"IEpYOvtYsdSw0xf5lHJM8aVwcNjB7BXNFPsvOJgHA4tDC/kxmKpxIH/2B624A/FCy9ChkyZqYL2GyuWVLQ76Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb4493e92ddb7ac762198607c5cee46620693112c2fdd69e84aab16dd468464e","last_reissued_at":"2026-07-05T08:25:35.340729Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:25:35.340729Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.19499","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:25:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yfHPIUL7Yt0bjjbCtFOhfz7wB5AvZ+ei1CoeKQtzLcdfDsppV4GPIs7MuXHB6fdDKyfzfzHlKPSiVsZpyZGZDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T03:03:06.285975Z"},"content_sha256":"ea064959b31d9c8123417677a24767dc451a049b39f5e510663a56dd6c6e51cf","schema_version":"1.0","event_id":"sha256:ea064959b31d9c8123417677a24767dc451a049b39f5e510663a56dd6c6e51cf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:XNCJH2JN3N5MOYQZQYD4LTXEMY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Momentum for the Win: Collaborative Federated Reinforcement Learning across Heterogeneous Environments","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.MA","math.OC"],"primary_cat":"cs.LG","authors_text":"Fei Miao, Han Wang, James Anderson, Sihong He, Zhili Zhang","submitted_at":"2024-05-29T20:24:42Z","abstract_excerpt":"We explore a Federated Reinforcement Learning (FRL) problem where $N$ agents collaboratively learn a common policy without sharing their trajectory data. To date, existing FRL work has primarily focused on agents operating in the same or ``similar\" environments. In contrast, our problem setup allows for arbitrarily large levels of environment heterogeneity. To obtain the optimal policy which maximizes the average performance across all potentially completely different environments, we propose two algorithms: FedSVRPG-M and FedHAPG-M. In contrast to existing results, we demonstrate that both Fe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.19499","kind":"arxiv","version":1},"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/2405.19499/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":"2026-07-05T08:25:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6iwEX++FRDU7+SL9uDRhlYNA8CWNqZd2zUSMITYhVGNvgiIaXjLdg6IPLkU14yw50TeSw6lem49w3gd2ZL6DDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T03:03:06.286618Z"},"content_sha256":"5d0a2bf0b77469991b2b500e7e1c771ffb3c0367de54cb70c05cc5b5866d1dc9","schema_version":"1.0","event_id":"sha256:5d0a2bf0b77469991b2b500e7e1c771ffb3c0367de54cb70c05cc5b5866d1dc9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XNCJH2JN3N5MOYQZQYD4LTXEMY/bundle.json","state_url":"https://pith.science/pith/XNCJH2JN3N5MOYQZQYD4LTXEMY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XNCJH2JN3N5MOYQZQYD4LTXEMY/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":"2026-07-08T03:03:06Z","links":{"resolver":"https://pith.science/pith/XNCJH2JN3N5MOYQZQYD4LTXEMY","bundle":"https://pith.science/pith/XNCJH2JN3N5MOYQZQYD4LTXEMY/bundle.json","state":"https://pith.science/pith/XNCJH2JN3N5MOYQZQYD4LTXEMY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XNCJH2JN3N5MOYQZQYD4LTXEMY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XNCJH2JN3N5MOYQZQYD4LTXEMY","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":"9c6176dedaa47780d8e6714e0bb6a75d60700a5a2f6cc04192ed858970052d36","cross_cats_sorted":["cs.MA","math.OC"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-29T20:24:42Z","title_canon_sha256":"5a7b3d72f4ffd39c80867b7b6de296df4c5e3db51e57c135697c590da1e7b0d9"},"schema_version":"1.0","source":{"id":"2405.19499","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.19499","created_at":"2026-07-05T08:25:35Z"},{"alias_kind":"arxiv_version","alias_value":"2405.19499v1","created_at":"2026-07-05T08:25:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.19499","created_at":"2026-07-05T08:25:35Z"},{"alias_kind":"pith_short_12","alias_value":"XNCJH2JN3N5M","created_at":"2026-07-05T08:25:35Z"},{"alias_kind":"pith_short_16","alias_value":"XNCJH2JN3N5MOYQZ","created_at":"2026-07-05T08:25:35Z"},{"alias_kind":"pith_short_8","alias_value":"XNCJH2JN","created_at":"2026-07-05T08:25:35Z"}],"graph_snapshots":[{"event_id":"sha256:5d0a2bf0b77469991b2b500e7e1c771ffb3c0367de54cb70c05cc5b5866d1dc9","target":"graph","created_at":"2026-07-05T08:25:35Z","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/2405.19499/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We explore a Federated Reinforcement Learning (FRL) problem where $N$ agents collaboratively learn a common policy without sharing their trajectory data. To date, existing FRL work has primarily focused on agents operating in the same or ``similar\" environments. In contrast, our problem setup allows for arbitrarily large levels of environment heterogeneity. To obtain the optimal policy which maximizes the average performance across all potentially completely different environments, we propose two algorithms: FedSVRPG-M and FedHAPG-M. In contrast to existing results, we demonstrate that both Fe","authors_text":"Fei Miao, Han Wang, James Anderson, Sihong He, Zhili Zhang","cross_cats":["cs.MA","math.OC"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-29T20:24:42Z","title":"Momentum for the Win: Collaborative Federated Reinforcement Learning across Heterogeneous Environments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.19499","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:ea064959b31d9c8123417677a24767dc451a049b39f5e510663a56dd6c6e51cf","target":"record","created_at":"2026-07-05T08:25:35Z","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":"9c6176dedaa47780d8e6714e0bb6a75d60700a5a2f6cc04192ed858970052d36","cross_cats_sorted":["cs.MA","math.OC"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-29T20:24:42Z","title_canon_sha256":"5a7b3d72f4ffd39c80867b7b6de296df4c5e3db51e57c135697c590da1e7b0d9"},"schema_version":"1.0","source":{"id":"2405.19499","kind":"arxiv","version":1}},"canonical_sha256":"bb4493e92ddb7ac762198607c5cee46620693112c2fdd69e84aab16dd468464e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bb4493e92ddb7ac762198607c5cee46620693112c2fdd69e84aab16dd468464e","first_computed_at":"2026-07-05T08:25:35.340729Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:25:35.340729Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IEpYOvtYsdSw0xf5lHJM8aVwcNjB7BXNFPsvOJgHA4tDC/kxmKpxIH/2B624A/FCy9ChkyZqYL2GyuWVLQ76Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:25:35.341174Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.19499","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ea064959b31d9c8123417677a24767dc451a049b39f5e510663a56dd6c6e51cf","sha256:5d0a2bf0b77469991b2b500e7e1c771ffb3c0367de54cb70c05cc5b5866d1dc9"],"state_sha256":"e647d049d790173eeee19b7262fbeca06ed05733c86ec117a6f3a11b093628f9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QpQRln0PaFVhVX+tIZfsBPRRmrPm2BzdNxEn9eQKi2BKDZIn7oR496VDNt7tLFwS5FDhNc6fXw3IVnWyC+DWBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T03:03:06.289947Z","bundle_sha256":"e4b4efcc207278a256ca2eb7537c56e30a44a4517d50c0f852f6902aa076056d"}}