{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:NUZONBMIKDYR2H4UKEWCLLUEOQ","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":"f9e3d6d7f4164dce5dfb4ca42b49ce9c7b8fe9b8488a1a6fbeff13ec74114515","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-02-27T02:29:01Z","title_canon_sha256":"10f354569def3c218e1d9350b5eb8bc3469c25efbb691a393af0bfbb75e463a1"},"schema_version":"1.0","source":{"id":"2103.00107","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.00107","created_at":"2026-07-05T02:19:02Z"},{"alias_kind":"arxiv_version","alias_value":"2103.00107v1","created_at":"2026-07-05T02:19:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.00107","created_at":"2026-07-05T02:19:02Z"},{"alias_kind":"pith_short_12","alias_value":"NUZONBMIKDYR","created_at":"2026-07-05T02:19:02Z"},{"alias_kind":"pith_short_16","alias_value":"NUZONBMIKDYR2H4U","created_at":"2026-07-05T02:19:02Z"},{"alias_kind":"pith_short_8","alias_value":"NUZONBMI","created_at":"2026-07-05T02:19:02Z"}],"graph_snapshots":[{"event_id":"sha256:f53025ca4e54b71a2263794924787b2f96c945eeae83214914d7c8eb475a477a","target":"graph","created_at":"2026-07-05T02:19:02Z","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/2103.00107/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Off-policy multi-step reinforcement learning algorithms consist of conservative and non-conservative algorithms: the former actively cut traces, whereas the latter do not. Recently, Munos et al. (2016) proved the convergence of conservative algorithms to an optimal Q-function. In contrast, non-conservative algorithms are thought to be unsafe and have a limited or no theoretical guarantee. Nonetheless, recent studies have shown that non-conservative algorithms empirically outperform conservative ones. Motivated by the empirical results and the lack of theory, we carry out theoretical analyses o","authors_text":"David Abel, Mark Rowland, Michal Valko, R\\'emi Munos, Steven Kapturowski, Tadashi Kozuno, Will Dabney, Yunhao Tang","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-02-27T02:29:01Z","title":"Revisiting Peng's Q($\\lambda$) for Modern Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.00107","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:bead0bf2cc87168686c478b73c8a7e3c687bfc1b24cfd70b357a2fae0758aa51","target":"record","created_at":"2026-07-05T02:19:02Z","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":"f9e3d6d7f4164dce5dfb4ca42b49ce9c7b8fe9b8488a1a6fbeff13ec74114515","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-02-27T02:29:01Z","title_canon_sha256":"10f354569def3c218e1d9350b5eb8bc3469c25efbb691a393af0bfbb75e463a1"},"schema_version":"1.0","source":{"id":"2103.00107","kind":"arxiv","version":1}},"canonical_sha256":"6d32e6858850f11d1f94512c25ae847425dd86f37e7c7d89d3773754b4cce05e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6d32e6858850f11d1f94512c25ae847425dd86f37e7c7d89d3773754b4cce05e","first_computed_at":"2026-07-05T02:19:02.430445Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:19:02.430445Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"q1ZXbQwh3JckGY3m2t0cjD9VLN2EELxYZThtDzXbX7GiN2Ui5sulcC6GuYOZs+4DeYvI21aU0n33LdxuA+f9Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:19:02.430916Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.00107","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bead0bf2cc87168686c478b73c8a7e3c687bfc1b24cfd70b357a2fae0758aa51","sha256:f53025ca4e54b71a2263794924787b2f96c945eeae83214914d7c8eb475a477a"],"state_sha256":"a8437f01fa38dbae14f0f4ff388f2f0851de24e001f31889b7b2eb20c36e3284"}