{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:NNGQRX3EUQ4J2RGBSCVCFSTAHK","short_pith_number":"pith:NNGQRX3E","schema_version":"1.0","canonical_sha256":"6b4d08df64a4389d44c190aa22ca603a9cc8aaae7be6229e1df93701913db14f","source":{"kind":"arxiv","id":"2109.09855","version":2},"attestation_state":"computed","paper":{"title":"Reinforcement Learning for Finite-Horizon Restless Multi-Armed Multi-Action Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Guojun Xiong, Jian Li, Rahul Singh","submitted_at":"2021-09-20T21:40:12Z","abstract_excerpt":"We study a finite-horizon restless multi-armed bandit problem with multiple actions, dubbed R(MA)^2B. The state of each arm evolves according to a controlled Markov decision process (MDP), and the reward of pulling an arm depends on both the current state of the corresponding MDP and the action taken. The goal is to sequentially choose actions for arms so as to maximize the expected value of the cumulative rewards collected. Since finding the optimal policy is typically intractable, we propose a computationally appealing index policy which we call Occupancy-Measured-Reward Index Policy. Our po"},"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":"2109.09855","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-20T21:40:12Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"1801ef0fd035004d07f2d0303ba5d113eb5c80a7a08207ce186bc48842406152","abstract_canon_sha256":"0efe0f6cc6cf81cc2acd0acc7b0ff47b9bb6f1ec79c652bbcc21010aaef3fd72"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:08:03.814863Z","signature_b64":"dJsbutv4a0o+eCOaoge3JgVJsPnMP6rCMIp5c1G3Si+I4vKMhrVAMP7qzwWXWfFNvytElzs6DkyGbne6GmLVAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b4d08df64a4389d44c190aa22ca603a9cc8aaae7be6229e1df93701913db14f","last_reissued_at":"2026-07-05T04:08:03.814456Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:08:03.814456Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning for Finite-Horizon Restless Multi-Armed Multi-Action Bandits","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Guojun Xiong, Jian Li, Rahul Singh","submitted_at":"2021-09-20T21:40:12Z","abstract_excerpt":"We study a finite-horizon restless multi-armed bandit problem with multiple actions, dubbed R(MA)^2B. The state of each arm evolves according to a controlled Markov decision process (MDP), and the reward of pulling an arm depends on both the current state of the corresponding MDP and the action taken. The goal is to sequentially choose actions for arms so as to maximize the expected value of the cumulative rewards collected. Since finding the optimal policy is typically intractable, we propose a computationally appealing index policy which we call Occupancy-Measured-Reward Index Policy. Our po"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.09855","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/2109.09855/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":"2109.09855","created_at":"2026-07-05T04:08:03.814513+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.09855v2","created_at":"2026-07-05T04:08:03.814513+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.09855","created_at":"2026-07-05T04:08:03.814513+00:00"},{"alias_kind":"pith_short_12","alias_value":"NNGQRX3EUQ4J","created_at":"2026-07-05T04:08:03.814513+00:00"},{"alias_kind":"pith_short_16","alias_value":"NNGQRX3EUQ4J2RGB","created_at":"2026-07-05T04:08:03.814513+00:00"},{"alias_kind":"pith_short_8","alias_value":"NNGQRX3E","created_at":"2026-07-05T04:08:03.814513+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/NNGQRX3EUQ4J2RGBSCVCFSTAHK","json":"https://pith.science/pith/NNGQRX3EUQ4J2RGBSCVCFSTAHK.json","graph_json":"https://pith.science/api/pith-number/NNGQRX3EUQ4J2RGBSCVCFSTAHK/graph.json","events_json":"https://pith.science/api/pith-number/NNGQRX3EUQ4J2RGBSCVCFSTAHK/events.json","paper":"https://pith.science/paper/NNGQRX3E"},"agent_actions":{"view_html":"https://pith.science/pith/NNGQRX3EUQ4J2RGBSCVCFSTAHK","download_json":"https://pith.science/pith/NNGQRX3EUQ4J2RGBSCVCFSTAHK.json","view_paper":"https://pith.science/paper/NNGQRX3E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.09855&json=true","fetch_graph":"https://pith.science/api/pith-number/NNGQRX3EUQ4J2RGBSCVCFSTAHK/graph.json","fetch_events":"https://pith.science/api/pith-number/NNGQRX3EUQ4J2RGBSCVCFSTAHK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NNGQRX3EUQ4J2RGBSCVCFSTAHK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NNGQRX3EUQ4J2RGBSCVCFSTAHK/action/storage_attestation","attest_author":"https://pith.science/pith/NNGQRX3EUQ4J2RGBSCVCFSTAHK/action/author_attestation","sign_citation":"https://pith.science/pith/NNGQRX3EUQ4J2RGBSCVCFSTAHK/action/citation_signature","submit_replication":"https://pith.science/pith/NNGQRX3EUQ4J2RGBSCVCFSTAHK/action/replication_record"}},"created_at":"2026-07-05T04:08:03.814513+00:00","updated_at":"2026-07-05T04:08:03.814513+00:00"}