{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HNHJBAP5E3KYQLGOTUCJJJXA7R","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":"07798d049c5663b0e5d734916fef229848e86a0d7ef1ab69ec3d151d3b567df7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-04T15:07:33Z","title_canon_sha256":"71b2a8a91181a46fd5487b297d869f95fbe9b1d0bf872df31cae3a20db3c0d70"},"schema_version":"1.0","source":{"id":"2403.02107","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.02107","created_at":"2026-07-05T10:43:35Z"},{"alias_kind":"arxiv_version","alias_value":"2403.02107v6","created_at":"2026-07-05T10:43:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.02107","created_at":"2026-07-05T10:43:35Z"},{"alias_kind":"pith_short_12","alias_value":"HNHJBAP5E3KY","created_at":"2026-07-05T10:43:35Z"},{"alias_kind":"pith_short_16","alias_value":"HNHJBAP5E3KYQLGO","created_at":"2026-07-05T10:43:35Z"},{"alias_kind":"pith_short_8","alias_value":"HNHJBAP5","created_at":"2026-07-05T10:43:35Z"}],"graph_snapshots":[{"event_id":"sha256:7cd585876976a58abe8f4a2e30d4a44e84d53ae4994c661f0772697c95736545","target":"graph","created_at":"2026-07-05T10:43:35Z","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/2403.02107/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Boris Belousov, Carlo D'Eramo, Daniel Palenicek, Jan Peters, Th\\'eo Vincent","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-04T15:07:33Z","title":"Iterated $Q$-Network: Beyond One-Step Bellman Updates in Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.02107","kind":"arxiv","version":6},"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":"sha256:47ccc89cdfe58eb3ba544eaebbef51dac22df10da4a050bcc60d03ce7cd3263e","target":"record","created_at":"2026-07-05T10:43:35Z","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":"07798d049c5663b0e5d734916fef229848e86a0d7ef1ab69ec3d151d3b567df7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2024-03-04T15:07:33Z","title_canon_sha256":"71b2a8a91181a46fd5487b297d869f95fbe9b1d0bf872df31cae3a20db3c0d70"},"schema_version":"1.0","source":{"id":"2403.02107","kind":"arxiv","version":6}},"canonical_sha256":"3b4e9081fd26d5882cce9d0494a6e0fc6fc07a17b39ed056300a17e0958327c7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3b4e9081fd26d5882cce9d0494a6e0fc6fc07a17b39ed056300a17e0958327c7","first_computed_at":"2026-07-05T10:43:35.167485Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:43:35.167485Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sYTx4S64uD0uLeffrEoWVVwiKzhwhdHoeMdq0Yfo9grlSb9uKMGmLzW8GFy1wYzjMUm7Cf3vRKmChBNBFWtmAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:43:35.167855Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.02107","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:47ccc89cdfe58eb3ba544eaebbef51dac22df10da4a050bcc60d03ce7cd3263e","sha256:7cd585876976a58abe8f4a2e30d4a44e84d53ae4994c661f0772697c95736545"],"state_sha256":"c72e3d9b64ca298891cb4514ed697659a3fe311cb7fae17e14a465649c7bf61c"}