{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BRMBSMR4XFL3HHGW3TOF2GXBWO","short_pith_number":"pith:BRMBSMR4","schema_version":"1.0","canonical_sha256":"0c5819323cb957b39cd6dcdc5d1ae1b3ac742f3964ec6c8399de58999552246d","source":{"kind":"arxiv","id":"2606.10835","version":1},"attestation_state":"computed","paper":{"title":"Geometrically Averaged Hard Target Updates for Linear Q-Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Donghwan Lee","submitted_at":"2026-06-09T13:24:36Z","abstract_excerpt":"Periodic hard target updates are among the most common stabilization devices in modern deep Q-learning. Recent studies suggest that target updates can improve stability in Q-learning with function approximation, including linear function approximation. We introduce and analyze the so-called $\\lambda$-target update, obtained by averaging the $m$-periodic target update maps with $\\lambda$-geometric weights $(1-\\lambda)\\lambda^{m-1}$, $\\lambda \\in [0,1]$. The endpoint $\\lambda=0$ recovers the one-period target update, while the continuous endpoint $\\lambda\\uparrow1$ recovers projected Q-value ite"},"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":"2606.10835","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-09T13:24:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bbbd46ab283f807e22b6fbb9542d86715038ca32e6d746e5d9d9214051f695a0","abstract_canon_sha256":"08cd153c87687c93d4fd439cca0865abf7acc693a7e0e305759da6aa550434b2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:10:43.131559Z","signature_b64":"A2zQmHtXzFvTM4GnZe+WnaF8YirWR5v+c2uzUAHffdDDLrauUa+RO1hb61HrWFVuDWgrmzgkgJ9Uw/MxS+8dCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c5819323cb957b39cd6dcdc5d1ae1b3ac742f3964ec6c8399de58999552246d","last_reissued_at":"2026-06-10T01:10:43.130539Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:10:43.130539Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Geometrically Averaged Hard Target Updates for Linear Q-Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Donghwan Lee","submitted_at":"2026-06-09T13:24:36Z","abstract_excerpt":"Periodic hard target updates are among the most common stabilization devices in modern deep Q-learning. Recent studies suggest that target updates can improve stability in Q-learning with function approximation, including linear function approximation. We introduce and analyze the so-called $\\lambda$-target update, obtained by averaging the $m$-periodic target update maps with $\\lambda$-geometric weights $(1-\\lambda)\\lambda^{m-1}$, $\\lambda \\in [0,1]$. The endpoint $\\lambda=0$ recovers the one-period target update, while the continuous endpoint $\\lambda\\uparrow1$ recovers projected Q-value ite"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10835","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/2606.10835/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":"2606.10835","created_at":"2026-06-10T01:10:43.130712+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.10835v1","created_at":"2026-06-10T01:10:43.130712+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10835","created_at":"2026-06-10T01:10:43.130712+00:00"},{"alias_kind":"pith_short_12","alias_value":"BRMBSMR4XFL3","created_at":"2026-06-10T01:10:43.130712+00:00"},{"alias_kind":"pith_short_16","alias_value":"BRMBSMR4XFL3HHGW","created_at":"2026-06-10T01:10:43.130712+00:00"},{"alias_kind":"pith_short_8","alias_value":"BRMBSMR4","created_at":"2026-06-10T01:10:43.130712+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/BRMBSMR4XFL3HHGW3TOF2GXBWO","json":"https://pith.science/pith/BRMBSMR4XFL3HHGW3TOF2GXBWO.json","graph_json":"https://pith.science/api/pith-number/BRMBSMR4XFL3HHGW3TOF2GXBWO/graph.json","events_json":"https://pith.science/api/pith-number/BRMBSMR4XFL3HHGW3TOF2GXBWO/events.json","paper":"https://pith.science/paper/BRMBSMR4"},"agent_actions":{"view_html":"https://pith.science/pith/BRMBSMR4XFL3HHGW3TOF2GXBWO","download_json":"https://pith.science/pith/BRMBSMR4XFL3HHGW3TOF2GXBWO.json","view_paper":"https://pith.science/paper/BRMBSMR4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.10835&json=true","fetch_graph":"https://pith.science/api/pith-number/BRMBSMR4XFL3HHGW3TOF2GXBWO/graph.json","fetch_events":"https://pith.science/api/pith-number/BRMBSMR4XFL3HHGW3TOF2GXBWO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BRMBSMR4XFL3HHGW3TOF2GXBWO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BRMBSMR4XFL3HHGW3TOF2GXBWO/action/storage_attestation","attest_author":"https://pith.science/pith/BRMBSMR4XFL3HHGW3TOF2GXBWO/action/author_attestation","sign_citation":"https://pith.science/pith/BRMBSMR4XFL3HHGW3TOF2GXBWO/action/citation_signature","submit_replication":"https://pith.science/pith/BRMBSMR4XFL3HHGW3TOF2GXBWO/action/replication_record"}},"created_at":"2026-06-10T01:10:43.130712+00:00","updated_at":"2026-06-10T01:10:43.130712+00:00"}