{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SZCEQXMGGWKJOZDEE57BY3J2GX","short_pith_number":"pith:SZCEQXMG","schema_version":"1.0","canonical_sha256":"9644485d863594976464277e1c6d3a35cb42d20dde6aac786f5760650cf06550","source":{"kind":"arxiv","id":"2506.19478","version":1},"attestation_state":"computed","paper":{"title":"ADDQ: Adaptive Distributional Double Q-Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Benedikt Wille, Leif D\\\"oring, Martin Slowik, Maximilian Birr, Mihail B\\^irsan","submitted_at":"2025-06-24T10:09:26Z","abstract_excerpt":"Bias problems in the estimation of $Q$-values are a well-known obstacle that slows down convergence of $Q$-learning and actor-critic methods. One of the reasons of the success of modern RL algorithms is partially a direct or indirect overestimation reduction mechanism. We propose an easy to implement method built on top of distributional reinforcement learning (DRL) algorithms to deal with the overestimation in a locally adaptive way. Our framework is simple to implement, existing distributional algorithms can be improved with a few lines of code. We provide theoretical evidence and use double"},"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":"2506.19478","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-24T10:09:26Z","cross_cats_sorted":["math.OC"],"title_canon_sha256":"d67ce12714b20b9ac0dec265a2a5d0b6a9c4e731936a7893ac2e4aa93f512f4c","abstract_canon_sha256":"ab23840b2fdda0a1d170d4e6546f054bf9dd618f4b5cd5da134b5dd9995c4642"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:26:54.081208Z","signature_b64":"SVaFEAre5eXcG0NNFoLo2eZW+cpfW3EuXrHbOjCqlnYd/S5ObIpfg5kJ8SgVreTeXlI7aKUalYdx9dcM+bEaBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9644485d863594976464277e1c6d3a35cb42d20dde6aac786f5760650cf06550","last_reissued_at":"2026-07-05T11:26:54.080739Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:26:54.080739Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ADDQ: Adaptive Distributional Double Q-Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["math.OC"],"primary_cat":"cs.LG","authors_text":"Benedikt Wille, Leif D\\\"oring, Martin Slowik, Maximilian Birr, Mihail B\\^irsan","submitted_at":"2025-06-24T10:09:26Z","abstract_excerpt":"Bias problems in the estimation of $Q$-values are a well-known obstacle that slows down convergence of $Q$-learning and actor-critic methods. One of the reasons of the success of modern RL algorithms is partially a direct or indirect overestimation reduction mechanism. We propose an easy to implement method built on top of distributional reinforcement learning (DRL) algorithms to deal with the overestimation in a locally adaptive way. Our framework is simple to implement, existing distributional algorithms can be improved with a few lines of code. We provide theoretical evidence and use double"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.19478","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/2506.19478/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":"2506.19478","created_at":"2026-07-05T11:26:54.080794+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.19478v1","created_at":"2026-07-05T11:26:54.080794+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.19478","created_at":"2026-07-05T11:26:54.080794+00:00"},{"alias_kind":"pith_short_12","alias_value":"SZCEQXMGGWKJ","created_at":"2026-07-05T11:26:54.080794+00:00"},{"alias_kind":"pith_short_16","alias_value":"SZCEQXMGGWKJOZDE","created_at":"2026-07-05T11:26:54.080794+00:00"},{"alias_kind":"pith_short_8","alias_value":"SZCEQXMG","created_at":"2026-07-05T11:26:54.080794+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/SZCEQXMGGWKJOZDEE57BY3J2GX","json":"https://pith.science/pith/SZCEQXMGGWKJOZDEE57BY3J2GX.json","graph_json":"https://pith.science/api/pith-number/SZCEQXMGGWKJOZDEE57BY3J2GX/graph.json","events_json":"https://pith.science/api/pith-number/SZCEQXMGGWKJOZDEE57BY3J2GX/events.json","paper":"https://pith.science/paper/SZCEQXMG"},"agent_actions":{"view_html":"https://pith.science/pith/SZCEQXMGGWKJOZDEE57BY3J2GX","download_json":"https://pith.science/pith/SZCEQXMGGWKJOZDEE57BY3J2GX.json","view_paper":"https://pith.science/paper/SZCEQXMG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.19478&json=true","fetch_graph":"https://pith.science/api/pith-number/SZCEQXMGGWKJOZDEE57BY3J2GX/graph.json","fetch_events":"https://pith.science/api/pith-number/SZCEQXMGGWKJOZDEE57BY3J2GX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SZCEQXMGGWKJOZDEE57BY3J2GX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SZCEQXMGGWKJOZDEE57BY3J2GX/action/storage_attestation","attest_author":"https://pith.science/pith/SZCEQXMGGWKJOZDEE57BY3J2GX/action/author_attestation","sign_citation":"https://pith.science/pith/SZCEQXMGGWKJOZDEE57BY3J2GX/action/citation_signature","submit_replication":"https://pith.science/pith/SZCEQXMGGWKJOZDEE57BY3J2GX/action/replication_record"}},"created_at":"2026-07-05T11:26:54.080794+00:00","updated_at":"2026-07-05T11:26:54.080794+00:00"}