{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HNHJBAP5E3KYQLGOTUCJJJXA7R","short_pith_number":"pith:HNHJBAP5","schema_version":"1.0","canonical_sha256":"3b4e9081fd26d5882cce9d0494a6e0fc6fc07a17b39ed056300a17e0958327c7","source":{"kind":"arxiv","id":"2403.02107","version":6},"attestation_state":"computed","paper":{"title":"Iterated $Q$-Network: Beyond One-Step Bellman Updates in Deep Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Boris Belousov, Carlo D'Eramo, Daniel Palenicek, Jan Peters, Th\\'eo Vincent","submitted_at":"2024-03-04T15:07:33Z","abstract_excerpt":"The vast majority of Reinforcement Learning methods is largely impacted by the computation effort and data requirements needed to obtain effective estimates of action-value functions, which in turn determine the quality of the overall performance and the sample-efficiency of the learning procedure. Typically, action-value functions are estimated through an iterative scheme that alternates the application of an empirical approximation of the Bellman operator and a subsequent projection step onto a considered function space. It has been observed that this scheme can be potentially generalized to"},"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":"2403.02107","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-04T15:07:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"71b2a8a91181a46fd5487b297d869f95fbe9b1d0bf872df31cae3a20db3c0d70","abstract_canon_sha256":"07798d049c5663b0e5d734916fef229848e86a0d7ef1ab69ec3d151d3b567df7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:43:35.167855Z","signature_b64":"sYTx4S64uD0uLeffrEoWVVwiKzhwhdHoeMdq0Yfo9grlSb9uKMGmLzW8GFy1wYzjMUm7Cf3vRKmChBNBFWtmAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b4e9081fd26d5882cce9d0494a6e0fc6fc07a17b39ed056300a17e0958327c7","last_reissued_at":"2026-07-05T10:43:35.167485Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:43:35.167485Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Iterated $Q$-Network: Beyond One-Step Bellman Updates in Deep Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Boris Belousov, Carlo D'Eramo, Daniel Palenicek, Jan Peters, Th\\'eo Vincent","submitted_at":"2024-03-04T15:07:33Z","abstract_excerpt":"The vast majority of Reinforcement Learning methods is largely impacted by the computation effort and data requirements needed to obtain effective estimates of action-value functions, which in turn determine the quality of the overall performance and the sample-efficiency of the learning procedure. Typically, action-value functions are estimated through an iterative scheme that alternates the application of an empirical approximation of the Bellman operator and a subsequent projection step onto a considered function space. It has been observed that this scheme can be potentially generalized to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.02107","kind":"arxiv","version":6},"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/2403.02107/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":"2403.02107","created_at":"2026-07-05T10:43:35.167542+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.02107v6","created_at":"2026-07-05T10:43:35.167542+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.02107","created_at":"2026-07-05T10:43:35.167542+00:00"},{"alias_kind":"pith_short_12","alias_value":"HNHJBAP5E3KY","created_at":"2026-07-05T10:43:35.167542+00:00"},{"alias_kind":"pith_short_16","alias_value":"HNHJBAP5E3KYQLGO","created_at":"2026-07-05T10:43:35.167542+00:00"},{"alias_kind":"pith_short_8","alias_value":"HNHJBAP5","created_at":"2026-07-05T10:43:35.167542+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/HNHJBAP5E3KYQLGOTUCJJJXA7R","json":"https://pith.science/pith/HNHJBAP5E3KYQLGOTUCJJJXA7R.json","graph_json":"https://pith.science/api/pith-number/HNHJBAP5E3KYQLGOTUCJJJXA7R/graph.json","events_json":"https://pith.science/api/pith-number/HNHJBAP5E3KYQLGOTUCJJJXA7R/events.json","paper":"https://pith.science/paper/HNHJBAP5"},"agent_actions":{"view_html":"https://pith.science/pith/HNHJBAP5E3KYQLGOTUCJJJXA7R","download_json":"https://pith.science/pith/HNHJBAP5E3KYQLGOTUCJJJXA7R.json","view_paper":"https://pith.science/paper/HNHJBAP5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.02107&json=true","fetch_graph":"https://pith.science/api/pith-number/HNHJBAP5E3KYQLGOTUCJJJXA7R/graph.json","fetch_events":"https://pith.science/api/pith-number/HNHJBAP5E3KYQLGOTUCJJJXA7R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HNHJBAP5E3KYQLGOTUCJJJXA7R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HNHJBAP5E3KYQLGOTUCJJJXA7R/action/storage_attestation","attest_author":"https://pith.science/pith/HNHJBAP5E3KYQLGOTUCJJJXA7R/action/author_attestation","sign_citation":"https://pith.science/pith/HNHJBAP5E3KYQLGOTUCJJJXA7R/action/citation_signature","submit_replication":"https://pith.science/pith/HNHJBAP5E3KYQLGOTUCJJJXA7R/action/replication_record"}},"created_at":"2026-07-05T10:43:35.167542+00:00","updated_at":"2026-07-05T10:43:35.167542+00:00"}