{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RJJBUJQFM6ONYLNAYFS6KV2YFG","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":"c891954de8b05c912e603a6dc1f0989184ce134ddcc2cba016c80e21c73785ed","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-30T21:32:46Z","title_canon_sha256":"2fc0788e021c07f303a9d0609328efc25f0a24d7e7a05a63195fc33cc8771345"},"schema_version":"1.0","source":{"id":"2507.00275","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.00275","created_at":"2026-05-20T00:00:21Z"},{"alias_kind":"arxiv_version","alias_value":"2507.00275v2","created_at":"2026-05-20T00:00:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00275","created_at":"2026-05-20T00:00:21Z"},{"alias_kind":"pith_short_12","alias_value":"RJJBUJQFM6ON","created_at":"2026-05-20T00:00:21Z"},{"alias_kind":"pith_short_16","alias_value":"RJJBUJQFM6ONYLNA","created_at":"2026-05-20T00:00:21Z"},{"alias_kind":"pith_short_8","alias_value":"RJJBUJQF","created_at":"2026-05-20T00:00:21Z"}],"graph_snapshots":[{"event_id":"sha256:e0e22c0ed85e9847d841fa0eee98f1e3276dd91f6e6f7e74438ae153b20afffb","target":"graph","created_at":"2026-05-20T00:00:21Z","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/2507.00275/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Double Q-learning is a classical control algorithm that mitigates the maximization bias of Q-learning. To do so, it explicitly trains two independent action-value functions and uses them to decouple action-selection and action-evaluation when computing bootstrap targets. Double DQN adapts target bootstrap decoupling to deep reinforcement learning (RL), but explicitly trains only a single action-value function and does not fully decouple its estimators. Consequently, the two estimators remain correlated, and overestimation persists. In this paper, we introduce Deep Double Q-learning (DDQL), a d","authors_text":"Marlos C. Machado, Martha White, Prabhat Nagarajan","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-30T21:32:46Z","title":"Deep Double Q-learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00275","kind":"arxiv","version":2},"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":"sha256:566e1b864bc376379c80c51a72bbc0cf43a27be16048ce892ce0b6e89a7d5b9e","target":"record","created_at":"2026-05-20T00:00:21Z","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":"c891954de8b05c912e603a6dc1f0989184ce134ddcc2cba016c80e21c73785ed","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-30T21:32:46Z","title_canon_sha256":"2fc0788e021c07f303a9d0609328efc25f0a24d7e7a05a63195fc33cc8771345"},"schema_version":"1.0","source":{"id":"2507.00275","kind":"arxiv","version":2}},"canonical_sha256":"8a521a2605679cdc2da0c165e5575829ae5500f0f4d87bd64c03fcf52d0a1159","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8a521a2605679cdc2da0c165e5575829ae5500f0f4d87bd64c03fcf52d0a1159","first_computed_at":"2026-05-20T00:00:21.773803Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:00:21.773803Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pxnOw2hcGofCVfC05lUZ9hcdfOmslqB77RM029pIGyTwx6rcillF+1w3OLQnGTRgNmgBsoSNmenQsZY5Zi+FBQ==","signature_status":"signed_v1","signed_at":"2026-05-20T00:00:21.774539Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.00275","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:566e1b864bc376379c80c51a72bbc0cf43a27be16048ce892ce0b6e89a7d5b9e","sha256:e0e22c0ed85e9847d841fa0eee98f1e3276dd91f6e6f7e74438ae153b20afffb"],"state_sha256":"401800ebfacec8d884f676b69fdb4ed60ae9ad8e044768b86aaf89d1a1c305c4"}