{"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"}