{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EGFGAG5W5IXJOEFNZXCOZQJRHU","short_pith_number":"pith:EGFGAG5W","schema_version":"1.0","canonical_sha256":"218a601bb6ea2e9710adcdc4ecc1313d375ad08d7d631225aa4b3ae903802ad2","source":{"kind":"arxiv","id":"2302.02212","version":2},"attestation_state":"computed","paper":{"title":"Federated Temporal Difference Learning with Linear Function Approximation under Environmental Heterogeneity","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Aritra Mitra, George J. Pappas, Hamed Hassani, Han Wang, James Anderson","submitted_at":"2023-02-04T17:53:55Z","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 "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2302.02212","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-04T17:53:55Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"052ae2859af0255a2aad9d83523277fa4b99137ef57b3eb171e9595f83d2e9b7","abstract_canon_sha256":"2ba6bedc39de4a43683aef9b5130ede73f10ccb91239265000abbbfeb866c4fe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:38:32.461355Z","signature_b64":"6PFNwlaVOO1Y1nMoIHt5hWpjfGb7canc0FlQkv9uwjuTf6Jrk2CjnZmmTJdOgexprmhowNbfzi8QD5Ru9KCMDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"218a601bb6ea2e9710adcdc4ecc1313d375ad08d7d631225aa4b3ae903802ad2","last_reissued_at":"2026-07-05T08:38:32.460875Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:38:32.460875Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Federated Temporal Difference Learning with Linear Function Approximation under Environmental Heterogeneity","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Aritra Mitra, George J. Pappas, Hamed Hassani, Han Wang, James Anderson","submitted_at":"2023-02-04T17:53:55Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.02212","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/2302.02212/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2302.02212","created_at":"2026-07-05T08:38:32.460932+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.02212v2","created_at":"2026-07-05T08:38:32.460932+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.02212","created_at":"2026-07-05T08:38:32.460932+00:00"},{"alias_kind":"pith_short_12","alias_value":"EGFGAG5W5IXJ","created_at":"2026-07-05T08:38:32.460932+00:00"},{"alias_kind":"pith_short_16","alias_value":"EGFGAG5W5IXJOEFN","created_at":"2026-07-05T08:38:32.460932+00:00"},{"alias_kind":"pith_short_8","alias_value":"EGFGAG5W","created_at":"2026-07-05T08:38:32.460932+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2409.03897","citing_title":"On the Convergence Rates of Federated Q-Learning across Heterogeneous Environments","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14423","citing_title":"Collaborative Yet Personalized Policy Training: Single-Timescale Federated Actor-Critic","ref_index":42,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EGFGAG5W5IXJOEFNZXCOZQJRHU","json":"https://pith.science/pith/EGFGAG5W5IXJOEFNZXCOZQJRHU.json","graph_json":"https://pith.science/api/pith-number/EGFGAG5W5IXJOEFNZXCOZQJRHU/graph.json","events_json":"https://pith.science/api/pith-number/EGFGAG5W5IXJOEFNZXCOZQJRHU/events.json","paper":"https://pith.science/paper/EGFGAG5W"},"agent_actions":{"view_html":"https://pith.science/pith/EGFGAG5W5IXJOEFNZXCOZQJRHU","download_json":"https://pith.science/pith/EGFGAG5W5IXJOEFNZXCOZQJRHU.json","view_paper":"https://pith.science/paper/EGFGAG5W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.02212&json=true","fetch_graph":"https://pith.science/api/pith-number/EGFGAG5W5IXJOEFNZXCOZQJRHU/graph.json","fetch_events":"https://pith.science/api/pith-number/EGFGAG5W5IXJOEFNZXCOZQJRHU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EGFGAG5W5IXJOEFNZXCOZQJRHU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EGFGAG5W5IXJOEFNZXCOZQJRHU/action/storage_attestation","attest_author":"https://pith.science/pith/EGFGAG5W5IXJOEFNZXCOZQJRHU/action/author_attestation","sign_citation":"https://pith.science/pith/EGFGAG5W5IXJOEFNZXCOZQJRHU/action/citation_signature","submit_replication":"https://pith.science/pith/EGFGAG5W5IXJOEFNZXCOZQJRHU/action/replication_record"}},"created_at":"2026-07-05T08:38:32.460932+00:00","updated_at":"2026-07-05T08:38:32.460932+00:00"}