{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3ZNTX2CD6GIZ6KBWJEULLKAG6M","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":"d735b2b455b00604441cdeb24a63aad0f7d6bf86706d765712d63c0fcd369412","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-14T06:41:15Z","title_canon_sha256":"92330b15e15d12a48b9ed1513a6a928028f648dce4c2b6c3297fa136f933c639"},"schema_version":"1.0","source":{"id":"2504.09929","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.09929","created_at":"2026-07-05T10:48:45Z"},{"alias_kind":"arxiv_version","alias_value":"2504.09929v1","created_at":"2026-07-05T10:48:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.09929","created_at":"2026-07-05T10:48:45Z"},{"alias_kind":"pith_short_12","alias_value":"3ZNTX2CD6GIZ","created_at":"2026-07-05T10:48:45Z"},{"alias_kind":"pith_short_16","alias_value":"3ZNTX2CD6GIZ6KBW","created_at":"2026-07-05T10:48:45Z"},{"alias_kind":"pith_short_8","alias_value":"3ZNTX2CD","created_at":"2026-07-05T10:48:45Z"}],"graph_snapshots":[{"event_id":"sha256:b6c1c15bd73b8d7579d3ea6edaf843d524e9715cfc7808a5f5df4a47b94a638a","target":"graph","created_at":"2026-07-05T10:48:45Z","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/2504.09929/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Overestimation is a fundamental characteristic of model-free reinforcement learning (MF-RL), arising from the principles of temporal difference learning and the approximation of the Q-function. To address this challenge, we propose a novel moderate target in the Q-function update, formulated as a convex optimization of an overestimated Q-function and its lower bound. Our primary contribution lies in the efficient estimation of this lower bound through the lower expectile of the Q-value distribution conditioned on a state. Notably, our moderate target integrates seamlessly into state-of-the-art","authors_text":"Songnam Hong, Ukjo Hwang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-14T06:41:15Z","title":"Moderate Actor-Critic Methods: Controlling Overestimation Bias via Expectile Loss"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.09929","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":"sha256:5a4446f42a83ed1c33addb1c55406f2727f3c2e493dc7a0deca739f664f69593","target":"record","created_at":"2026-07-05T10:48:45Z","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":"d735b2b455b00604441cdeb24a63aad0f7d6bf86706d765712d63c0fcd369412","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-14T06:41:15Z","title_canon_sha256":"92330b15e15d12a48b9ed1513a6a928028f648dce4c2b6c3297fa136f933c639"},"schema_version":"1.0","source":{"id":"2504.09929","kind":"arxiv","version":1}},"canonical_sha256":"de5b3be843f1919f28364928b5a806f3376d366da969daa8dd44149d5ca36ee1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"de5b3be843f1919f28364928b5a806f3376d366da969daa8dd44149d5ca36ee1","first_computed_at":"2026-07-05T10:48:45.027507Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:48:45.027507Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/Zbh85tLyrrgVKqyv+ZcuWK/PP1KwOTd75CKTIsdqQ30NvJvM66/wq2/KkWCv/QUwanaKaJKi+okcfOm493dDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:48:45.028048Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.09929","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5a4446f42a83ed1c33addb1c55406f2727f3c2e493dc7a0deca739f664f69593","sha256:b6c1c15bd73b8d7579d3ea6edaf843d524e9715cfc7808a5f5df4a47b94a638a"],"state_sha256":"e795bbb1b70433c23b7c4333f2cb18daa7cfb58af482aef4df183e52368eacea"}