{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:FS33GFSGJWHULP2HUOUHPSRHFI","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":"8e037adb53143c6ad7f76b176d6baced6465020869bd5287a1f2af565ea5719d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-03T10:30:56Z","title_canon_sha256":"7669d41187197c84215673cd983553d7a015d5a135d79dea81c0a5d0d7cbb1ff"},"schema_version":"1.0","source":{"id":"2608.02034","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.02034","created_at":"2026-08-04T02:10:32Z"},{"alias_kind":"arxiv_version","alias_value":"2608.02034v1","created_at":"2026-08-04T02:10:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.02034","created_at":"2026-08-04T02:10:32Z"},{"alias_kind":"pith_short_12","alias_value":"FS33GFSGJWHU","created_at":"2026-08-04T02:10:32Z"},{"alias_kind":"pith_short_16","alias_value":"FS33GFSGJWHULP2H","created_at":"2026-08-04T02:10:32Z"},{"alias_kind":"pith_short_8","alias_value":"FS33GFSG","created_at":"2026-08-04T02:10:32Z"}],"graph_snapshots":[{"event_id":"sha256:34146d80ea685d9ebdaf27181289b70931fd55fd26302cdd6078053ead0d8593","target":"graph","created_at":"2026-08-04T02:10:32Z","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/2608.02034/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-step returns accelerate reward propagation in off-policy reinforcement learning, but couple the evaluation of each decision to the suboptimal logged actions that follow it, inducing a pessimistic bias that grows with the horizon. We propose Expectile $n$-step Q-learning (ENQ), which replaces the symmetric $n$-step temporal-difference (TD) loss with an asymmetric expectile loss on the action-value error, with expectile level $\\tau$ as the only method-specific hyperparameter added beyond $n$-step TD. We prove that the ENQ operator is a $\\gamma^{n}$-contraction. Under deterministic dynamics","authors_text":"Abdelghani Ghanem, Mounir Ghogho","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-03T10:30:56Z","title":"Upper-Expectile Multi-Step Q-Learning for Off-Policy Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.02034","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":"sha256:540b4b1f182edd1998746e1e650fd72a4272e6a51120424378faa885d7daf8fb","target":"record","created_at":"2026-08-04T02:10:32Z","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":"8e037adb53143c6ad7f76b176d6baced6465020869bd5287a1f2af565ea5719d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-03T10:30:56Z","title_canon_sha256":"7669d41187197c84215673cd983553d7a015d5a135d79dea81c0a5d0d7cbb1ff"},"schema_version":"1.0","source":{"id":"2608.02034","kind":"arxiv","version":1}},"canonical_sha256":"2cb7b316464d8f45bf47a3a877ca272a184401a982af03300a4adc2de25b5086","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2cb7b316464d8f45bf47a3a877ca272a184401a982af03300a4adc2de25b5086","first_computed_at":"2026-08-04T02:10:32.902633Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-04T02:10:32.902633Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UPHEnS81DNmMtDj3ORbQO2drakCP13Dkm7/BKNd6UtfLbYWvvyRhjH3WkMBsyw2KYIFYCYNPvDrGNR6B/VXWDQ==","signature_status":"signed_v1","signed_at":"2026-08-04T02:10:32.904573Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.02034","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:540b4b1f182edd1998746e1e650fd72a4272e6a51120424378faa885d7daf8fb","sha256:34146d80ea685d9ebdaf27181289b70931fd55fd26302cdd6078053ead0d8593"],"state_sha256":"4657cbab22c6bba8e949ce1223f6694ae47118eee3b9a319fc60ccabdda16c33"}