{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:NUZONBMIKDYR2H4UKEWCLLUEOQ","short_pith_number":"pith:NUZONBMI","schema_version":"1.0","canonical_sha256":"6d32e6858850f11d1f94512c25ae847425dd86f37e7c7d89d3773754b4cce05e","source":{"kind":"arxiv","id":"2103.00107","version":1},"attestation_state":"computed","paper":{"title":"Revisiting Peng's Q($\\lambda$) for Modern Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"David Abel, Mark Rowland, Michal Valko, R\\'emi Munos, Steven Kapturowski, Tadashi Kozuno, Will Dabney, Yunhao Tang","submitted_at":"2021-02-27T02:29:01Z","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"},"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":"2103.00107","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-02-27T02:29:01Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"10f354569def3c218e1d9350b5eb8bc3469c25efbb691a393af0bfbb75e463a1","abstract_canon_sha256":"f9e3d6d7f4164dce5dfb4ca42b49ce9c7b8fe9b8488a1a6fbeff13ec74114515"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:19:02.430916Z","signature_b64":"q1ZXbQwh3JckGY3m2t0cjD9VLN2EELxYZThtDzXbX7GiN2Ui5sulcC6GuYOZs+4DeYvI21aU0n33LdxuA+f9Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d32e6858850f11d1f94512c25ae847425dd86f37e7c7d89d3773754b4cce05e","last_reissued_at":"2026-07-05T02:19:02.430445Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:19:02.430445Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Revisiting Peng's Q($\\lambda$) for Modern Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"David Abel, Mark Rowland, Michal Valko, R\\'emi Munos, Steven Kapturowski, Tadashi Kozuno, Will Dabney, Yunhao Tang","submitted_at":"2021-02-27T02:29:01Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.00107","kind":"arxiv","version":1},"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/2103.00107/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":"2103.00107","created_at":"2026-07-05T02:19:02.430517+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.00107v1","created_at":"2026-07-05T02:19:02.430517+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.00107","created_at":"2026-07-05T02:19:02.430517+00:00"},{"alias_kind":"pith_short_12","alias_value":"NUZONBMIKDYR","created_at":"2026-07-05T02:19:02.430517+00:00"},{"alias_kind":"pith_short_16","alias_value":"NUZONBMIKDYR2H4U","created_at":"2026-07-05T02:19:02.430517+00:00"},{"alias_kind":"pith_short_8","alias_value":"NUZONBMI","created_at":"2026-07-05T02:19:02.430517+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/NUZONBMIKDYR2H4UKEWCLLUEOQ","json":"https://pith.science/pith/NUZONBMIKDYR2H4UKEWCLLUEOQ.json","graph_json":"https://pith.science/api/pith-number/NUZONBMIKDYR2H4UKEWCLLUEOQ/graph.json","events_json":"https://pith.science/api/pith-number/NUZONBMIKDYR2H4UKEWCLLUEOQ/events.json","paper":"https://pith.science/paper/NUZONBMI"},"agent_actions":{"view_html":"https://pith.science/pith/NUZONBMIKDYR2H4UKEWCLLUEOQ","download_json":"https://pith.science/pith/NUZONBMIKDYR2H4UKEWCLLUEOQ.json","view_paper":"https://pith.science/paper/NUZONBMI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.00107&json=true","fetch_graph":"https://pith.science/api/pith-number/NUZONBMIKDYR2H4UKEWCLLUEOQ/graph.json","fetch_events":"https://pith.science/api/pith-number/NUZONBMIKDYR2H4UKEWCLLUEOQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NUZONBMIKDYR2H4UKEWCLLUEOQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NUZONBMIKDYR2H4UKEWCLLUEOQ/action/storage_attestation","attest_author":"https://pith.science/pith/NUZONBMIKDYR2H4UKEWCLLUEOQ/action/author_attestation","sign_citation":"https://pith.science/pith/NUZONBMIKDYR2H4UKEWCLLUEOQ/action/citation_signature","submit_replication":"https://pith.science/pith/NUZONBMIKDYR2H4UKEWCLLUEOQ/action/replication_record"}},"created_at":"2026-07-05T02:19:02.430517+00:00","updated_at":"2026-07-05T02:19:02.430517+00:00"}