{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:ONCSUXUBDYYH3OYZJ4P4EKXBV4","short_pith_number":"pith:ONCSUXUB","schema_version":"1.0","canonical_sha256":"73452a5e811e307dbb194f1fc22ae1af2854242111f8199621d3872fed918ece","source":{"kind":"arxiv","id":"2206.10185","version":2},"attestation_state":"computed","paper":{"title":"Federated Stochastic Approximation under Markov Noise and Heterogeneity: Applications in Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Gauri Joshi, Pranay Sharma, Sajad Khodadadian, Siva Theja Maguluri","submitted_at":"2022-06-21T08:39:12Z","abstract_excerpt":"Since reinforcement learning algorithms are notoriously data-intensive, the task of sampling observations from the environment is usually split across multiple agents. However, transferring these observations from the agents to a central location can be prohibitively expensive in terms of communication cost, and it can also compromise the privacy of each agent's local behavior policy. Federated reinforcement learning is a framework in which $N$ agents collaboratively learn a global model, without sharing their individual data and policies. This global model is the unique fixed point of the ave"},"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":"2206.10185","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-21T08:39:12Z","cross_cats_sorted":[],"title_canon_sha256":"0f7e99f2e40dcb1a0dcaed380ae05e700593edf70e03c5af9a786d7493112d52","abstract_canon_sha256":"d21a5fd5ae625c84cb46fc125b803c83e13090c2c580ea648e7fa1455399c22b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:22:57.856708Z","signature_b64":"Ce/U8B24+DUuceXMxzFbk+RI3S6G3THWzd4aEtLUrgCB40pfLe3zpCZlTAbz338BpCE2I7A8Ps4zQ+moWKq7Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73452a5e811e307dbb194f1fc22ae1af2854242111f8199621d3872fed918ece","last_reissued_at":"2026-07-05T09:22:57.856330Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:22:57.856330Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Federated Stochastic Approximation under Markov Noise and Heterogeneity: Applications in Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Gauri Joshi, Pranay Sharma, Sajad Khodadadian, Siva Theja Maguluri","submitted_at":"2022-06-21T08:39:12Z","abstract_excerpt":"Since reinforcement learning algorithms are notoriously data-intensive, the task of sampling observations from the environment is usually split across multiple agents. However, transferring these observations from the agents to a central location can be prohibitively expensive in terms of communication cost, and it can also compromise the privacy of each agent's local behavior policy. Federated reinforcement learning is a framework in which $N$ agents collaboratively learn a global model, without sharing their individual data and policies. This global model is the unique fixed point of the ave"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.10185","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/2206.10185/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":"2206.10185","created_at":"2026-07-05T09:22:57.856391+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.10185v2","created_at":"2026-07-05T09:22:57.856391+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.10185","created_at":"2026-07-05T09:22:57.856391+00:00"},{"alias_kind":"pith_short_12","alias_value":"ONCSUXUBDYYH","created_at":"2026-07-05T09:22:57.856391+00:00"},{"alias_kind":"pith_short_16","alias_value":"ONCSUXUBDYYH3OYZ","created_at":"2026-07-05T09:22:57.856391+00:00"},{"alias_kind":"pith_short_8","alias_value":"ONCSUXUB","created_at":"2026-07-05T09:22:57.856391+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ONCSUXUBDYYH3OYZJ4P4EKXBV4","json":"https://pith.science/pith/ONCSUXUBDYYH3OYZJ4P4EKXBV4.json","graph_json":"https://pith.science/api/pith-number/ONCSUXUBDYYH3OYZJ4P4EKXBV4/graph.json","events_json":"https://pith.science/api/pith-number/ONCSUXUBDYYH3OYZJ4P4EKXBV4/events.json","paper":"https://pith.science/paper/ONCSUXUB"},"agent_actions":{"view_html":"https://pith.science/pith/ONCSUXUBDYYH3OYZJ4P4EKXBV4","download_json":"https://pith.science/pith/ONCSUXUBDYYH3OYZJ4P4EKXBV4.json","view_paper":"https://pith.science/paper/ONCSUXUB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.10185&json=true","fetch_graph":"https://pith.science/api/pith-number/ONCSUXUBDYYH3OYZJ4P4EKXBV4/graph.json","fetch_events":"https://pith.science/api/pith-number/ONCSUXUBDYYH3OYZJ4P4EKXBV4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ONCSUXUBDYYH3OYZJ4P4EKXBV4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ONCSUXUBDYYH3OYZJ4P4EKXBV4/action/storage_attestation","attest_author":"https://pith.science/pith/ONCSUXUBDYYH3OYZJ4P4EKXBV4/action/author_attestation","sign_citation":"https://pith.science/pith/ONCSUXUBDYYH3OYZJ4P4EKXBV4/action/citation_signature","submit_replication":"https://pith.science/pith/ONCSUXUBDYYH3OYZJ4P4EKXBV4/action/replication_record"}},"created_at":"2026-07-05T09:22:57.856391+00:00","updated_at":"2026-07-05T09:22:57.856391+00:00"}