{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:EGFGAG5W5IXJOEFNZXCOZQJRHU","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":"2ba6bedc39de4a43683aef9b5130ede73f10ccb91239265000abbbfeb866c4fe","cross_cats_sorted":["math.OC"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-04T17:53:55Z","title_canon_sha256":"052ae2859af0255a2aad9d83523277fa4b99137ef57b3eb171e9595f83d2e9b7"},"schema_version":"1.0","source":{"id":"2302.02212","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.02212","created_at":"2026-07-05T08:38:32Z"},{"alias_kind":"arxiv_version","alias_value":"2302.02212v2","created_at":"2026-07-05T08:38:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.02212","created_at":"2026-07-05T08:38:32Z"},{"alias_kind":"pith_short_12","alias_value":"EGFGAG5W5IXJ","created_at":"2026-07-05T08:38:32Z"},{"alias_kind":"pith_short_16","alias_value":"EGFGAG5W5IXJOEFN","created_at":"2026-07-05T08:38:32Z"},{"alias_kind":"pith_short_8","alias_value":"EGFGAG5W","created_at":"2026-07-05T08:38:32Z"}],"graph_snapshots":[{"event_id":"sha256:62ecf260ad6476abbcaec9c4608004d050fb8badc58662272387e8a47d2f9319","target":"graph","created_at":"2026-07-05T08:38:32Z","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/2302.02212/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We initiate the study of federated reinforcement learning under environmental heterogeneity by considering a policy evaluation problem. Our setup involves $N$ agents interacting with environments that share the same state and action space but differ in their reward functions and state transition kernels. Assuming agents can communicate via a central server, we ask: Does exchanging information expedite the process of evaluating a common policy? To answer this question, we provide the first comprehensive finite-time analysis of a federated temporal difference (TD) learning algorithm with linear ","authors_text":"Aritra Mitra, George J. Pappas, Hamed Hassani, Han Wang, James Anderson","cross_cats":["math.OC"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-04T17:53:55Z","title":"Federated Temporal Difference Learning with Linear Function Approximation under Environmental Heterogeneity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.02212","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:db908dc6c89ae31751bc893525ffd75c254e71cd927a3d5079535d1f52b09fa9","target":"record","created_at":"2026-07-05T08:38:32Z","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":"2ba6bedc39de4a43683aef9b5130ede73f10ccb91239265000abbbfeb866c4fe","cross_cats_sorted":["math.OC"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-04T17:53:55Z","title_canon_sha256":"052ae2859af0255a2aad9d83523277fa4b99137ef57b3eb171e9595f83d2e9b7"},"schema_version":"1.0","source":{"id":"2302.02212","kind":"arxiv","version":2}},"canonical_sha256":"218a601bb6ea2e9710adcdc4ecc1313d375ad08d7d631225aa4b3ae903802ad2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"218a601bb6ea2e9710adcdc4ecc1313d375ad08d7d631225aa4b3ae903802ad2","first_computed_at":"2026-07-05T08:38:32.460875Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:38:32.460875Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6PFNwlaVOO1Y1nMoIHt5hWpjfGb7canc0FlQkv9uwjuTf6Jrk2CjnZmmTJdOgexprmhowNbfzi8QD5Ru9KCMDA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:38:32.461355Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.02212","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:db908dc6c89ae31751bc893525ffd75c254e71cd927a3d5079535d1f52b09fa9","sha256:62ecf260ad6476abbcaec9c4608004d050fb8badc58662272387e8a47d2f9319"],"state_sha256":"95d94657ea9f73066e2320f6e3a47c2c288f81d9e532d325995df33ab357f26f"}