{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:IJKP4FFB3EMTB6LWXPBXIYVRF5","short_pith_number":"pith:IJKP4FFB","schema_version":"1.0","canonical_sha256":"4254fe14a1d91930f976bbc37462b12f47b3c96b43c4644fefb3d882ef3366d3","source":{"kind":"arxiv","id":"2605.20592","version":1},"attestation_state":"computed","paper":{"title":"ReversedQ: Opportunities for Faster Q-Learning in Episodic Online Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aviva Prins, Sofia R. Miskala-Dinc","submitted_at":"2026-05-20T00:58:07Z","abstract_excerpt":"We study model-free Q-learning in finite-horizon episodic Markov Decision Processes (MDPs) with stationary dynamics across episodes. We identify a central issue in nascent model-free posterior-sampling works: the reliance on delayed learning in order to prove theoretical guarantees. In particular, we identify three opportunities for faster learning - (i) value-function update order, (ii) update frequencies, and (iii) value-function initialization. Using Wang et al.'s RandomizedQ as a basis, we illustrate these changes and their individual (as well as cumulative) impact in multiple empirical st"},"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":"2605.20592","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T00:58:07Z","cross_cats_sorted":[],"title_canon_sha256":"fe94470218da3ea2163c0ec7b2b202e2993ed60c8fe8a9244d93655d95bc0afa","abstract_canon_sha256":"ea10a70a8432052644522787a8a9b79e234b2c3da316771f6e60d0f8bcca46fe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:04:43.812780Z","signature_b64":"LRocbRRfqTiTbFcF6Nd35Y5o8XuuCP8kxzHgvJjZE/FQg/nG5MVY+75c+6r3lZwhtms+OZrQcMm9y0Vu2bhRBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4254fe14a1d91930f976bbc37462b12f47b3c96b43c4644fefb3d882ef3366d3","last_reissued_at":"2026-05-21T01:04:43.812245Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:04:43.812245Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ReversedQ: Opportunities for Faster Q-Learning in Episodic Online Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aviva Prins, Sofia R. Miskala-Dinc","submitted_at":"2026-05-20T00:58:07Z","abstract_excerpt":"We study model-free Q-learning in finite-horizon episodic Markov Decision Processes (MDPs) with stationary dynamics across episodes. We identify a central issue in nascent model-free posterior-sampling works: the reliance on delayed learning in order to prove theoretical guarantees. In particular, we identify three opportunities for faster learning - (i) value-function update order, (ii) update frequencies, and (iii) value-function initialization. Using Wang et al.'s RandomizedQ as a basis, we illustrate these changes and their individual (as well as cumulative) impact in multiple empirical st"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20592","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/2605.20592/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":"2605.20592","created_at":"2026-05-21T01:04:43.812333+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.20592v1","created_at":"2026-05-21T01:04:43.812333+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20592","created_at":"2026-05-21T01:04:43.812333+00:00"},{"alias_kind":"pith_short_12","alias_value":"IJKP4FFB3EMT","created_at":"2026-05-21T01:04:43.812333+00:00"},{"alias_kind":"pith_short_16","alias_value":"IJKP4FFB3EMTB6LW","created_at":"2026-05-21T01:04:43.812333+00:00"},{"alias_kind":"pith_short_8","alias_value":"IJKP4FFB","created_at":"2026-05-21T01:04:43.812333+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/IJKP4FFB3EMTB6LWXPBXIYVRF5","json":"https://pith.science/pith/IJKP4FFB3EMTB6LWXPBXIYVRF5.json","graph_json":"https://pith.science/api/pith-number/IJKP4FFB3EMTB6LWXPBXIYVRF5/graph.json","events_json":"https://pith.science/api/pith-number/IJKP4FFB3EMTB6LWXPBXIYVRF5/events.json","paper":"https://pith.science/paper/IJKP4FFB"},"agent_actions":{"view_html":"https://pith.science/pith/IJKP4FFB3EMTB6LWXPBXIYVRF5","download_json":"https://pith.science/pith/IJKP4FFB3EMTB6LWXPBXIYVRF5.json","view_paper":"https://pith.science/paper/IJKP4FFB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.20592&json=true","fetch_graph":"https://pith.science/api/pith-number/IJKP4FFB3EMTB6LWXPBXIYVRF5/graph.json","fetch_events":"https://pith.science/api/pith-number/IJKP4FFB3EMTB6LWXPBXIYVRF5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IJKP4FFB3EMTB6LWXPBXIYVRF5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IJKP4FFB3EMTB6LWXPBXIYVRF5/action/storage_attestation","attest_author":"https://pith.science/pith/IJKP4FFB3EMTB6LWXPBXIYVRF5/action/author_attestation","sign_citation":"https://pith.science/pith/IJKP4FFB3EMTB6LWXPBXIYVRF5/action/citation_signature","submit_replication":"https://pith.science/pith/IJKP4FFB3EMTB6LWXPBXIYVRF5/action/replication_record"}},"created_at":"2026-05-21T01:04:43.812333+00:00","updated_at":"2026-05-21T01:04:43.812333+00:00"}