{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:ONCSUXUBDYYH3OYZJ4P4EKXBV4","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":"d21a5fd5ae625c84cb46fc125b803c83e13090c2c580ea648e7fa1455399c22b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-21T08:39:12Z","title_canon_sha256":"0f7e99f2e40dcb1a0dcaed380ae05e700593edf70e03c5af9a786d7493112d52"},"schema_version":"1.0","source":{"id":"2206.10185","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.10185","created_at":"2026-07-05T09:22:57Z"},{"alias_kind":"arxiv_version","alias_value":"2206.10185v2","created_at":"2026-07-05T09:22:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.10185","created_at":"2026-07-05T09:22:57Z"},{"alias_kind":"pith_short_12","alias_value":"ONCSUXUBDYYH","created_at":"2026-07-05T09:22:57Z"},{"alias_kind":"pith_short_16","alias_value":"ONCSUXUBDYYH3OYZ","created_at":"2026-07-05T09:22:57Z"},{"alias_kind":"pith_short_8","alias_value":"ONCSUXUB","created_at":"2026-07-05T09:22:57Z"}],"graph_snapshots":[{"event_id":"sha256:7abadc62f86bb144ec89579aa1e6f712b6693f6dab4d1fa3544761f458aaf7e6","target":"graph","created_at":"2026-07-05T09:22:57Z","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/2206.10185/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Gauri Joshi, Pranay Sharma, Sajad Khodadadian, Siva Theja Maguluri","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-21T08:39:12Z","title":"Federated Stochastic Approximation under Markov Noise and Heterogeneity: Applications in Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.10185","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":"sha256:1287eda75f1b34eedfeafb99e15ee76957d3cc88ea102ace79946f2cc4f7ef50","target":"record","created_at":"2026-07-05T09:22:57Z","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":"d21a5fd5ae625c84cb46fc125b803c83e13090c2c580ea648e7fa1455399c22b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-21T08:39:12Z","title_canon_sha256":"0f7e99f2e40dcb1a0dcaed380ae05e700593edf70e03c5af9a786d7493112d52"},"schema_version":"1.0","source":{"id":"2206.10185","kind":"arxiv","version":2}},"canonical_sha256":"73452a5e811e307dbb194f1fc22ae1af2854242111f8199621d3872fed918ece","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"73452a5e811e307dbb194f1fc22ae1af2854242111f8199621d3872fed918ece","first_computed_at":"2026-07-05T09:22:57.856330Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:22:57.856330Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ce/U8B24+DUuceXMxzFbk+RI3S6G3THWzd4aEtLUrgCB40pfLe3zpCZlTAbz338BpCE2I7A8Ps4zQ+moWKq7Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:22:57.856708Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.10185","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1287eda75f1b34eedfeafb99e15ee76957d3cc88ea102ace79946f2cc4f7ef50","sha256:7abadc62f86bb144ec89579aa1e6f712b6693f6dab4d1fa3544761f458aaf7e6"],"state_sha256":"e23106e663f773cff8a068291bba877a73eea4a254a8b2961305dd9734703bd6"}