{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BQ4SSWEVR5LOFHUP2ADXN2FBMO","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":"36a81a903ab782418360792ca74f413acf7453cba59eafb2fcb1c3f795a90b7e","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-22T15:42:43Z","title_canon_sha256":"0e7b4e44cf3feb6d38a9e2b981cd9a3896228af656e7ecbb92c520c962b8d91b"},"schema_version":"1.0","source":{"id":"2411.15014","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.15014","created_at":"2026-07-05T11:38:25Z"},{"alias_kind":"arxiv_version","alias_value":"2411.15014v2","created_at":"2026-07-05T11:38:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.15014","created_at":"2026-07-05T11:38:25Z"},{"alias_kind":"pith_short_12","alias_value":"BQ4SSWEVR5LO","created_at":"2026-07-05T11:38:25Z"},{"alias_kind":"pith_short_16","alias_value":"BQ4SSWEVR5LOFHUP","created_at":"2026-07-05T11:38:25Z"},{"alias_kind":"pith_short_8","alias_value":"BQ4SSWEV","created_at":"2026-07-05T11:38:25Z"}],"graph_snapshots":[{"event_id":"sha256:a244bb037a6ecbad8055288dc8c2fb57c20a33b274d821a5a6845c48f71cde8f","target":"graph","created_at":"2026-07-05T11:38:25Z","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/2411.15014/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Federated reinforcement learning (FedRL) enables multiple agents to collaboratively learn a policy without sharing their local trajectories collected during agent-environment interactions. However, in practice, the environments faced by different agents are often heterogeneous, leading to poor performance by the single policy learned by existing FedRL algorithms on individual agents. In this paper, we take a further step and introduce a \\emph{personalized} FedRL framework (PFedRL) by taking advantage of possibly shared common structure among agents in heterogeneous environments. Specifically, ","authors_text":"Daniel Jiang, Guojun Xiong, Jian Li, Shufan Wang","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-22T15:42:43Z","title":"On the Linear Speedup of Personalized Federated Reinforcement Learning with Shared Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.15014","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":"sha256:7d39806d9dbd62620661ec246e294391bb396a9d3bcd57b5c2c4ef20a0d7aa93","target":"record","created_at":"2026-07-05T11:38:25Z","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":"36a81a903ab782418360792ca74f413acf7453cba59eafb2fcb1c3f795a90b7e","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-22T15:42:43Z","title_canon_sha256":"0e7b4e44cf3feb6d38a9e2b981cd9a3896228af656e7ecbb92c520c962b8d91b"},"schema_version":"1.0","source":{"id":"2411.15014","kind":"arxiv","version":2}},"canonical_sha256":"0c392958958f56e29e8fd00776e8a1638e7fcc2377d62798ad478e36bef0b460","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0c392958958f56e29e8fd00776e8a1638e7fcc2377d62798ad478e36bef0b460","first_computed_at":"2026-07-05T11:38:25.512144Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:38:25.512144Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wtvUrsikrDWfLfhisfLOukCf79cNiiBx83fDmV60lpJ7T/s0jIA5fo8pOOe23sF0jMwtqfIN9cn00nUSct6RCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:38:25.512707Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.15014","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7d39806d9dbd62620661ec246e294391bb396a9d3bcd57b5c2c4ef20a0d7aa93","sha256:a244bb037a6ecbad8055288dc8c2fb57c20a33b274d821a5a6845c48f71cde8f"],"state_sha256":"e897680516300116c428811cc23f1357caf4ead422570f75492cb5e5063463e8"}