{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EBUHBL5SOEK7OK7ZBFWRYW2UKF","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":"72f7eaf1376dcf10abc77b66404ee587a65e578889b080eb1ef465654d11f580","cross_cats_sorted":["cs.SY","eess.SY","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-06T20:24:19Z","title_canon_sha256":"6e8c17f86439b8979afce2f904b64b04cd622098db0ff2683d5555b51adc9bc5"},"schema_version":"1.0","source":{"id":"2409.04605","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.04605","created_at":"2026-07-05T09:04:15Z"},{"alias_kind":"arxiv_version","alias_value":"2409.04605v1","created_at":"2026-07-05T09:04:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.04605","created_at":"2026-07-05T09:04:15Z"},{"alias_kind":"pith_short_12","alias_value":"EBUHBL5SOEK7","created_at":"2026-07-05T09:04:15Z"},{"alias_kind":"pith_short_16","alias_value":"EBUHBL5SOEK7OK7Z","created_at":"2026-07-05T09:04:15Z"},{"alias_kind":"pith_short_8","alias_value":"EBUHBL5S","created_at":"2026-07-05T09:04:15Z"}],"graph_snapshots":[{"event_id":"sha256:7cd1d14cd7ceea74e0e9b32702d2e80f068829c3f1f1532a83d05a098190bb59","target":"graph","created_at":"2026-07-05T09:04:15Z","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/2409.04605/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the Whittle index learning algorithm for restless multi-armed bandits. We consider index learning algorithm with Q-learning. We first present Q-learning algorithm with exploration policies -- epsilon-greedy, softmax, epsilon-softmax with constant stepsizes. We extend the study of Q-learning to index learning for single-armed restless bandit. The algorithm of index learning is two-timescale variant of stochastic approximation, on slower timescale we update index learning scheme and on faster timescale we update Q-learning assuming fixed index value. In Q-learning updates are in asynchr","authors_text":"Rahul Meshram, Surya Prakash, Vishesh Mittal","cross_cats":["cs.SY","eess.SY","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-06T20:24:19Z","title":"Whittle Index Learning Algorithms for Restless Bandits with Constant Stepsizes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.04605","kind":"arxiv","version":1},"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":"sha256:23be71bc7379016c8eee8a9a941a29912a0e99705db36d5f8c4eee73fece2492","target":"record","created_at":"2026-07-05T09:04:15Z","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":"72f7eaf1376dcf10abc77b66404ee587a65e578889b080eb1ef465654d11f580","cross_cats_sorted":["cs.SY","eess.SY","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-06T20:24:19Z","title_canon_sha256":"6e8c17f86439b8979afce2f904b64b04cd622098db0ff2683d5555b51adc9bc5"},"schema_version":"1.0","source":{"id":"2409.04605","kind":"arxiv","version":1}},"canonical_sha256":"206870afb27115f72bf9096d1c5b545163c4040ea3ff42fa61d9cd1a1c268d0b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"206870afb27115f72bf9096d1c5b545163c4040ea3ff42fa61d9cd1a1c268d0b","first_computed_at":"2026-07-05T09:04:15.112064Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:04:15.112064Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pX9rShoc0pnGZb99XJRl7o53BZtx78LGpfH64HXWnqIGWDVYnXlPdcxU/M8zIMsIgxt/vCl63nOW+hPwBNufDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:04:15.112480Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.04605","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:23be71bc7379016c8eee8a9a941a29912a0e99705db36d5f8c4eee73fece2492","sha256:7cd1d14cd7ceea74e0e9b32702d2e80f068829c3f1f1532a83d05a098190bb59"],"state_sha256":"456d06240da2eb34db554cf3095a03308eb5f7c12cee8a5130aef9fb929ac2bd"}