{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SZCEQXMGGWKJOZDEE57BY3J2GX","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":"ab23840b2fdda0a1d170d4e6546f054bf9dd618f4b5cd5da134b5dd9995c4642","cross_cats_sorted":["math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-24T10:09:26Z","title_canon_sha256":"d67ce12714b20b9ac0dec265a2a5d0b6a9c4e731936a7893ac2e4aa93f512f4c"},"schema_version":"1.0","source":{"id":"2506.19478","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.19478","created_at":"2026-07-05T11:26:54Z"},{"alias_kind":"arxiv_version","alias_value":"2506.19478v1","created_at":"2026-07-05T11:26:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.19478","created_at":"2026-07-05T11:26:54Z"},{"alias_kind":"pith_short_12","alias_value":"SZCEQXMGGWKJ","created_at":"2026-07-05T11:26:54Z"},{"alias_kind":"pith_short_16","alias_value":"SZCEQXMGGWKJOZDE","created_at":"2026-07-05T11:26:54Z"},{"alias_kind":"pith_short_8","alias_value":"SZCEQXMG","created_at":"2026-07-05T11:26:54Z"}],"graph_snapshots":[{"event_id":"sha256:6efce9fd7ce1f9291e153b34a824bf2b25e334ae11fdc6d85841755002f66d72","target":"graph","created_at":"2026-07-05T11:26:54Z","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/2506.19478/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Benedikt Wille, Leif D\\\"oring, Martin Slowik, Maximilian Birr, Mihail B\\^irsan","cross_cats":["math.OC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-24T10:09:26Z","title":"ADDQ: Adaptive Distributional Double Q-Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.19478","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:c08e40970164046e6748e833b5cc81db566fcc693773a6296206602672c49e85","target":"record","created_at":"2026-07-05T11:26:54Z","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":"ab23840b2fdda0a1d170d4e6546f054bf9dd618f4b5cd5da134b5dd9995c4642","cross_cats_sorted":["math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-24T10:09:26Z","title_canon_sha256":"d67ce12714b20b9ac0dec265a2a5d0b6a9c4e731936a7893ac2e4aa93f512f4c"},"schema_version":"1.0","source":{"id":"2506.19478","kind":"arxiv","version":1}},"canonical_sha256":"9644485d863594976464277e1c6d3a35cb42d20dde6aac786f5760650cf06550","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9644485d863594976464277e1c6d3a35cb42d20dde6aac786f5760650cf06550","first_computed_at":"2026-07-05T11:26:54.080739Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:26:54.080739Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SVaFEAre5eXcG0NNFoLo2eZW+cpfW3EuXrHbOjCqlnYd/S5ObIpfg5kJ8SgVreTeXlI7aKUalYdx9dcM+bEaBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:26:54.081208Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.19478","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c08e40970164046e6748e833b5cc81db566fcc693773a6296206602672c49e85","sha256:6efce9fd7ce1f9291e153b34a824bf2b25e334ae11fdc6d85841755002f66d72"],"state_sha256":"00f92e1ff716b3997b30dd76dd24e8d5118425a0679698fa4c679482cab43428"}