{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:NNGQRX3EUQ4J2RGBSCVCFSTAHK","short_pith_number":"pith:NNGQRX3E","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"},"canonical_sha256":"6b4d08df64a4389d44c190aa22ca603a9cc8aaae7be6229e1df93701913db14f","source":{"kind":"arxiv","id":"2109.09855","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.09855","created_at":"2026-07-05T04:08:03Z"},{"alias_kind":"arxiv_version","alias_value":"2109.09855v2","created_at":"2026-07-05T04:08:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.09855","created_at":"2026-07-05T04:08:03Z"},{"alias_kind":"pith_short_12","alias_value":"NNGQRX3EUQ4J","created_at":"2026-07-05T04:08:03Z"},{"alias_kind":"pith_short_16","alias_value":"NNGQRX3EUQ4J2RGB","created_at":"2026-07-05T04:08:03Z"},{"alias_kind":"pith_short_8","alias_value":"NNGQRX3E","created_at":"2026-07-05T04:08:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:NNGQRX3EUQ4J2RGBSCVCFSTAHK","target":"record","payload":{"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"},"canonical_sha256":"6b4d08df64a4389d44c190aa22ca603a9cc8aaae7be6229e1df93701913db14f","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"},"source_kind":"arxiv","source_id":"2109.09855","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:08:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iT9N3S/aUFP5VlF9zBXLSqKm9fZ8psHrFywHbhVMYO7pHOUwIwblJqwtguP9NN+ljpFstneVfSkrLcHNfG4LBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T12:20:46.012309Z"},"content_sha256":"8b111ced7b5359cf2431167d384fcbf3a2e911ce68455c43d2ebd5016234eb01","schema_version":"1.0","event_id":"sha256:8b111ced7b5359cf2431167d384fcbf3a2e911ce68455c43d2ebd5016234eb01"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:NNGQRX3EUQ4J2RGBSCVCFSTAHK","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:08:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LRdh1pS1GIuuexWLLTtEJbjUJO02okqAXS81Apx0Ukj5lKBcnBFsOrjGz+d6zalmVxP46FNtWOzxxt/aRtxgBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T12:20:46.012729Z"},"content_sha256":"bf18402430cdd00c3e4207dedfef7f87dd2bc176ecc00a28b1cf1d846b3a12b6","schema_version":"1.0","event_id":"sha256:bf18402430cdd00c3e4207dedfef7f87dd2bc176ecc00a28b1cf1d846b3a12b6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NNGQRX3EUQ4J2RGBSCVCFSTAHK/bundle.json","state_url":"https://pith.science/pith/NNGQRX3EUQ4J2RGBSCVCFSTAHK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NNGQRX3EUQ4J2RGBSCVCFSTAHK/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-06T12:20:46Z","links":{"resolver":"https://pith.science/pith/NNGQRX3EUQ4J2RGBSCVCFSTAHK","bundle":"https://pith.science/pith/NNGQRX3EUQ4J2RGBSCVCFSTAHK/bundle.json","state":"https://pith.science/pith/NNGQRX3EUQ4J2RGBSCVCFSTAHK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NNGQRX3EUQ4J2RGBSCVCFSTAHK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:NNGQRX3EUQ4J2RGBSCVCFSTAHK","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":"0efe0f6cc6cf81cc2acd0acc7b0ff47b9bb6f1ec79c652bbcc21010aaef3fd72","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-20T21:40:12Z","title_canon_sha256":"1801ef0fd035004d07f2d0303ba5d113eb5c80a7a08207ce186bc48842406152"},"schema_version":"1.0","source":{"id":"2109.09855","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.09855","created_at":"2026-07-05T04:08:03Z"},{"alias_kind":"arxiv_version","alias_value":"2109.09855v2","created_at":"2026-07-05T04:08:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.09855","created_at":"2026-07-05T04:08:03Z"},{"alias_kind":"pith_short_12","alias_value":"NNGQRX3EUQ4J","created_at":"2026-07-05T04:08:03Z"},{"alias_kind":"pith_short_16","alias_value":"NNGQRX3EUQ4J2RGB","created_at":"2026-07-05T04:08:03Z"},{"alias_kind":"pith_short_8","alias_value":"NNGQRX3E","created_at":"2026-07-05T04:08:03Z"}],"graph_snapshots":[{"event_id":"sha256:bf18402430cdd00c3e4207dedfef7f87dd2bc176ecc00a28b1cf1d846b3a12b6","target":"graph","created_at":"2026-07-05T04:08:03Z","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/2109.09855/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Guojun Xiong, Jian Li, Rahul Singh","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-20T21:40:12Z","title":"Reinforcement Learning for Finite-Horizon Restless Multi-Armed Multi-Action Bandits"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.09855","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":"sha256:8b111ced7b5359cf2431167d384fcbf3a2e911ce68455c43d2ebd5016234eb01","target":"record","created_at":"2026-07-05T04:08:03Z","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":"0efe0f6cc6cf81cc2acd0acc7b0ff47b9bb6f1ec79c652bbcc21010aaef3fd72","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-20T21:40:12Z","title_canon_sha256":"1801ef0fd035004d07f2d0303ba5d113eb5c80a7a08207ce186bc48842406152"},"schema_version":"1.0","source":{"id":"2109.09855","kind":"arxiv","version":2}},"canonical_sha256":"6b4d08df64a4389d44c190aa22ca603a9cc8aaae7be6229e1df93701913db14f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6b4d08df64a4389d44c190aa22ca603a9cc8aaae7be6229e1df93701913db14f","first_computed_at":"2026-07-05T04:08:03.814456Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:08:03.814456Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dJsbutv4a0o+eCOaoge3JgVJsPnMP6rCMIp5c1G3Si+I4vKMhrVAMP7qzwWXWfFNvytElzs6DkyGbne6GmLVAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:08:03.814863Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.09855","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8b111ced7b5359cf2431167d384fcbf3a2e911ce68455c43d2ebd5016234eb01","sha256:bf18402430cdd00c3e4207dedfef7f87dd2bc176ecc00a28b1cf1d846b3a12b6"],"state_sha256":"0460a34b1c657fc49191475f719e6e14575aba75cfb55a8b9aac2fd2099d5ca5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g3I2PZaDtPaBcQCcsAQ2TmaoEebU+761uom34vWolVMTmLf68rns97YGT2qJT7usRK3cYwPLv3OotpAcTD0TCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T12:20:46.014938Z","bundle_sha256":"3ce79135a4c797e1b65cf504c7f3f2c37ee79db96dc139f89d46e3506e95855e"}}