{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:S54YIR3E6HZGHCI2CZUOTIOOGL","short_pith_number":"pith:S54YIR3E","schema_version":"1.0","canonical_sha256":"9779844764f1f263891a1668e9a1ce32dbeed2d271b9b5e83c327d2059422a09","source":{"kind":"arxiv","id":"2405.00950","version":1},"attestation_state":"computed","paper":{"title":"Provably Efficient Reinforcement Learning for Adversarial Restless Multi-Armed Bandits with Unknown Transitions and Bandit Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Guojun Xiong, Jian Li","submitted_at":"2024-05-02T02:20:19Z","abstract_excerpt":"Restless multi-armed bandits (RMAB) play a central role in modeling sequential decision making problems under an instantaneous activation constraint that at most B arms can be activated at any decision epoch. Each restless arm is endowed with a state that evolves independently according to a Markov decision process regardless of being activated or not. In this paper, we consider the task of learning in episodic RMAB with unknown transition functions and adversarial rewards, which can change arbitrarily across episodes. Further, we consider a challenging but natural bandit feedback setting that"},"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":"2405.00950","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-02T02:20:19Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"8687ca78af2cf9256b9f2bd86932954284d17e684e7fa12a1bb722a714d60374","abstract_canon_sha256":"0ac1b5be7454ec2373530023c92b18c4a03bfaeade6145a75ec75ed4b3de80d3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:14:28.407400Z","signature_b64":"rFG/ncPzuFKq6meNOns8UbXKHwUXlZ6BhasklAZb1OcC4n28VH1jioRfd6U5xXrEpoLksNXulWpsCIe/gK+1BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9779844764f1f263891a1668e9a1ce32dbeed2d271b9b5e83c327d2059422a09","last_reissued_at":"2026-07-05T08:14:28.406912Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:14:28.406912Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Provably Efficient Reinforcement Learning for Adversarial Restless Multi-Armed Bandits with Unknown Transitions and Bandit Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Guojun Xiong, Jian Li","submitted_at":"2024-05-02T02:20:19Z","abstract_excerpt":"Restless multi-armed bandits (RMAB) play a central role in modeling sequential decision making problems under an instantaneous activation constraint that at most B arms can be activated at any decision epoch. Each restless arm is endowed with a state that evolves independently according to a Markov decision process regardless of being activated or not. In this paper, we consider the task of learning in episodic RMAB with unknown transition functions and adversarial rewards, which can change arbitrarily across episodes. Further, we consider a challenging but natural bandit feedback setting that"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.00950","kind":"arxiv","version":1},"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/2405.00950/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":"2405.00950","created_at":"2026-07-05T08:14:28.406969+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.00950v1","created_at":"2026-07-05T08:14:28.406969+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.00950","created_at":"2026-07-05T08:14:28.406969+00:00"},{"alias_kind":"pith_short_12","alias_value":"S54YIR3E6HZG","created_at":"2026-07-05T08:14:28.406969+00:00"},{"alias_kind":"pith_short_16","alias_value":"S54YIR3E6HZGHCI2","created_at":"2026-07-05T08:14:28.406969+00:00"},{"alias_kind":"pith_short_8","alias_value":"S54YIR3E","created_at":"2026-07-05T08:14:28.406969+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.10177","citing_title":"A Modularized Framework for Piecewise-Stationary Restless Bandits","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S54YIR3E6HZGHCI2CZUOTIOOGL","json":"https://pith.science/pith/S54YIR3E6HZGHCI2CZUOTIOOGL.json","graph_json":"https://pith.science/api/pith-number/S54YIR3E6HZGHCI2CZUOTIOOGL/graph.json","events_json":"https://pith.science/api/pith-number/S54YIR3E6HZGHCI2CZUOTIOOGL/events.json","paper":"https://pith.science/paper/S54YIR3E"},"agent_actions":{"view_html":"https://pith.science/pith/S54YIR3E6HZGHCI2CZUOTIOOGL","download_json":"https://pith.science/pith/S54YIR3E6HZGHCI2CZUOTIOOGL.json","view_paper":"https://pith.science/paper/S54YIR3E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.00950&json=true","fetch_graph":"https://pith.science/api/pith-number/S54YIR3E6HZGHCI2CZUOTIOOGL/graph.json","fetch_events":"https://pith.science/api/pith-number/S54YIR3E6HZGHCI2CZUOTIOOGL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S54YIR3E6HZGHCI2CZUOTIOOGL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S54YIR3E6HZGHCI2CZUOTIOOGL/action/storage_attestation","attest_author":"https://pith.science/pith/S54YIR3E6HZGHCI2CZUOTIOOGL/action/author_attestation","sign_citation":"https://pith.science/pith/S54YIR3E6HZGHCI2CZUOTIOOGL/action/citation_signature","submit_replication":"https://pith.science/pith/S54YIR3E6HZGHCI2CZUOTIOOGL/action/replication_record"}},"created_at":"2026-07-05T08:14:28.406969+00:00","updated_at":"2026-07-05T08:14:28.406969+00:00"}