{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:VW2FL7IDYSEQIDIFGB5OQMFUWV","short_pith_number":"pith:VW2FL7ID","schema_version":"1.0","canonical_sha256":"adb455fd03c489040d05307ae830b4b56d2f29705f96c2260047710a33f3d0ef","source":{"kind":"arxiv","id":"2108.11887","version":2},"attestation_state":"computed","paper":{"title":"Federated Reinforcement Learning: Techniques, Applications, and Open Challenges","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jiaju Qi, Kan Zheng, Lei Lei, Qihao Zhou","submitted_at":"2021-08-26T16:22:49Z","abstract_excerpt":"This paper presents a comprehensive survey of Federated Reinforcement Learning (FRL), an emerging and promising field in Reinforcement Learning (RL). Starting with a tutorial of Federated Learning (FL) and RL, we then focus on the introduction of FRL as a new method with great potential by leveraging the basic idea of FL to improve the performance of RL while preserving data-privacy. According to the distribution characteristics of the agents in the framework, FRL algorithms can be divided into two categories, i.e. Horizontal Federated Reinforcement Learning (HFRL) and Vertical Federated Reinf"},"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":"2108.11887","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-08-26T16:22:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d0a93621e061bfc680600566131aea8357dc5ae09d3c28a69da929b2b510983a","abstract_canon_sha256":"2fc1b4949672feced1fe6df58c247bbfbfdc08ea80baac793fb84daa5f8ce102"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:09:03.440647Z","signature_b64":"0aK/qVD7AGZnjDllvp9jt5zzVFQuaRFw7KmLFJBA634esRI5UOYDmY1EFUtWL/NqR3vS+cFp3DLslEokR5ycDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"adb455fd03c489040d05307ae830b4b56d2f29705f96c2260047710a33f3d0ef","last_reissued_at":"2026-07-05T06:09:03.440214Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:09:03.440214Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Federated Reinforcement Learning: Techniques, Applications, and Open Challenges","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jiaju Qi, Kan Zheng, Lei Lei, Qihao Zhou","submitted_at":"2021-08-26T16:22:49Z","abstract_excerpt":"This paper presents a comprehensive survey of Federated Reinforcement Learning (FRL), an emerging and promising field in Reinforcement Learning (RL). Starting with a tutorial of Federated Learning (FL) and RL, we then focus on the introduction of FRL as a new method with great potential by leveraging the basic idea of FL to improve the performance of RL while preserving data-privacy. According to the distribution characteristics of the agents in the framework, FRL algorithms can be divided into two categories, i.e. Horizontal Federated Reinforcement Learning (HFRL) and Vertical Federated Reinf"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.11887","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/2108.11887/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":"2108.11887","created_at":"2026-07-05T06:09:03.440268+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.11887v2","created_at":"2026-07-05T06:09:03.440268+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.11887","created_at":"2026-07-05T06:09:03.440268+00:00"},{"alias_kind":"pith_short_12","alias_value":"VW2FL7IDYSEQ","created_at":"2026-07-05T06:09:03.440268+00:00"},{"alias_kind":"pith_short_16","alias_value":"VW2FL7IDYSEQIDIF","created_at":"2026-07-05T06:09:03.440268+00:00"},{"alias_kind":"pith_short_8","alias_value":"VW2FL7ID","created_at":"2026-07-05T06:09:03.440268+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.29002","citing_title":"FedQHD: Closed-Form Function-Space Federated Reinforcement Learning","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08268","citing_title":"Insider Attacks in Multi-Agent LLM Consensus Systems","ref_index":223,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08378","citing_title":"Reinforcement Learning for Scalable and Trustworthy Intelligent Systems","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05088","citing_title":"Scalar Federated Learning for Linear Quadratic Regulator","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02165","citing_title":"Experience Constrained Hierarchical Federated Reinforcement Learning for Large-scale UAV Teams in Hazardous Environments","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VW2FL7IDYSEQIDIFGB5OQMFUWV","json":"https://pith.science/pith/VW2FL7IDYSEQIDIFGB5OQMFUWV.json","graph_json":"https://pith.science/api/pith-number/VW2FL7IDYSEQIDIFGB5OQMFUWV/graph.json","events_json":"https://pith.science/api/pith-number/VW2FL7IDYSEQIDIFGB5OQMFUWV/events.json","paper":"https://pith.science/paper/VW2FL7ID"},"agent_actions":{"view_html":"https://pith.science/pith/VW2FL7IDYSEQIDIFGB5OQMFUWV","download_json":"https://pith.science/pith/VW2FL7IDYSEQIDIFGB5OQMFUWV.json","view_paper":"https://pith.science/paper/VW2FL7ID","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.11887&json=true","fetch_graph":"https://pith.science/api/pith-number/VW2FL7IDYSEQIDIFGB5OQMFUWV/graph.json","fetch_events":"https://pith.science/api/pith-number/VW2FL7IDYSEQIDIFGB5OQMFUWV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VW2FL7IDYSEQIDIFGB5OQMFUWV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VW2FL7IDYSEQIDIFGB5OQMFUWV/action/storage_attestation","attest_author":"https://pith.science/pith/VW2FL7IDYSEQIDIFGB5OQMFUWV/action/author_attestation","sign_citation":"https://pith.science/pith/VW2FL7IDYSEQIDIFGB5OQMFUWV/action/citation_signature","submit_replication":"https://pith.science/pith/VW2FL7IDYSEQIDIFGB5OQMFUWV/action/replication_record"}},"created_at":"2026-07-05T06:09:03.440268+00:00","updated_at":"2026-07-05T06:09:03.440268+00:00"}