{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:LZ2IRGANJNAEQKOCB6GUVYZQ6C","short_pith_number":"pith:LZ2IRGAN","schema_version":"1.0","canonical_sha256":"5e7488980d4b404829c20f8d4ae330f0a7e8152e04caa0c00f2e36f0ac8d5148","source":{"kind":"arxiv","id":"1805.07956","version":2},"attestation_state":"computed","paper":{"title":"Multiple-Step Greedy Policies in Online and Approximate Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bruno Scherrer, Gal Dalal, Shie Mannor, Yonathan Efroni","submitted_at":"2018-05-21T09:17:09Z","abstract_excerpt":"Multiple-step lookahead policies have demonstrated high empirical competence in Reinforcement Learning, via the use of Monte Carlo Tree Search or Model Predictive Control. In a recent work \\cite{efroni2018beyond}, multiple-step greedy policies and their use in vanilla Policy Iteration algorithms were proposed and analyzed. In this work, we study multiple-step greedy algorithms in more practical setups. We begin by highlighting a counter-intuitive difficulty, arising with soft-policy updates: even in the absence of approximations, and contrary to the 1-step-greedy case, monotonic policy improve"},"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":"1805.07956","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-21T09:17:09Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"89d3a4d0def796079131485ac9fe29df306e2b23478b05397e2f35b8b46ab28e","abstract_canon_sha256":"63a5730266373af09a6ab39434a77482ba062ff93b3422e68b6cebc56ec5aa14"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:05:19.253834Z","signature_b64":"ZxDmm1EJy0jXijlonUGlU/84bKy06Wvrp8PyA5U4GoxHc5gPcduPNtMs3pch2mg2RXHVPEkand92XRgyV0nyBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e7488980d4b404829c20f8d4ae330f0a7e8152e04caa0c00f2e36f0ac8d5148","last_reissued_at":"2026-05-18T00:05:19.253327Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:05:19.253327Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multiple-Step Greedy Policies in Online and Approximate Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bruno Scherrer, Gal Dalal, Shie Mannor, Yonathan Efroni","submitted_at":"2018-05-21T09:17:09Z","abstract_excerpt":"Multiple-step lookahead policies have demonstrated high empirical competence in Reinforcement Learning, via the use of Monte Carlo Tree Search or Model Predictive Control. In a recent work \\cite{efroni2018beyond}, multiple-step greedy policies and their use in vanilla Policy Iteration algorithms were proposed and analyzed. In this work, we study multiple-step greedy algorithms in more practical setups. We begin by highlighting a counter-intuitive difficulty, arising with soft-policy updates: even in the absence of approximations, and contrary to the 1-step-greedy case, monotonic policy improve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.07956","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1805.07956","created_at":"2026-05-18T00:05:19.253398+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.07956v2","created_at":"2026-05-18T00:05:19.253398+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.07956","created_at":"2026-05-18T00:05:19.253398+00:00"},{"alias_kind":"pith_short_12","alias_value":"LZ2IRGANJNAE","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_16","alias_value":"LZ2IRGANJNAEQKOC","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_8","alias_value":"LZ2IRGAN","created_at":"2026-05-18T12:32:37.024351+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/LZ2IRGANJNAEQKOCB6GUVYZQ6C","json":"https://pith.science/pith/LZ2IRGANJNAEQKOCB6GUVYZQ6C.json","graph_json":"https://pith.science/api/pith-number/LZ2IRGANJNAEQKOCB6GUVYZQ6C/graph.json","events_json":"https://pith.science/api/pith-number/LZ2IRGANJNAEQKOCB6GUVYZQ6C/events.json","paper":"https://pith.science/paper/LZ2IRGAN"},"agent_actions":{"view_html":"https://pith.science/pith/LZ2IRGANJNAEQKOCB6GUVYZQ6C","download_json":"https://pith.science/pith/LZ2IRGANJNAEQKOCB6GUVYZQ6C.json","view_paper":"https://pith.science/paper/LZ2IRGAN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.07956&json=true","fetch_graph":"https://pith.science/api/pith-number/LZ2IRGANJNAEQKOCB6GUVYZQ6C/graph.json","fetch_events":"https://pith.science/api/pith-number/LZ2IRGANJNAEQKOCB6GUVYZQ6C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LZ2IRGANJNAEQKOCB6GUVYZQ6C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LZ2IRGANJNAEQKOCB6GUVYZQ6C/action/storage_attestation","attest_author":"https://pith.science/pith/LZ2IRGANJNAEQKOCB6GUVYZQ6C/action/author_attestation","sign_citation":"https://pith.science/pith/LZ2IRGANJNAEQKOCB6GUVYZQ6C/action/citation_signature","submit_replication":"https://pith.science/pith/LZ2IRGANJNAEQKOCB6GUVYZQ6C/action/replication_record"}},"created_at":"2026-05-18T00:05:19.253398+00:00","updated_at":"2026-05-18T00:05:19.253398+00:00"}