{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:LZ2IRGANJNAEQKOCB6GUVYZQ6C","short_pith_number":"pith:LZ2IRGAN","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"},"canonical_sha256":"5e7488980d4b404829c20f8d4ae330f0a7e8152e04caa0c00f2e36f0ac8d5148","source":{"kind":"arxiv","id":"1805.07956","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.07956","created_at":"2026-05-18T00:05:19Z"},{"alias_kind":"arxiv_version","alias_value":"1805.07956v2","created_at":"2026-05-18T00:05:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.07956","created_at":"2026-05-18T00:05:19Z"},{"alias_kind":"pith_short_12","alias_value":"LZ2IRGANJNAE","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"LZ2IRGANJNAEQKOC","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"LZ2IRGAN","created_at":"2026-05-18T12:32:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:LZ2IRGANJNAEQKOCB6GUVYZQ6C","target":"record","payload":{"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"},"canonical_sha256":"5e7488980d4b404829c20f8d4ae330f0a7e8152e04caa0c00f2e36f0ac8d5148","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"},"source_kind":"arxiv","source_id":"1805.07956","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:05:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6heGrNo5FcbPATT1rFRVxlb6VdKmiJwKf8cGRh4+ET5v61qDQ/goCyjynEcVOvDl0v0cW3VDJKOPKEoWpP3sBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T08:36:14.835725Z"},"content_sha256":"bbaf82ea2eb58134ac0fafdbe186b4e8464104fa102f524b33823dc33c1defe2","schema_version":"1.0","event_id":"sha256:bbaf82ea2eb58134ac0fafdbe186b4e8464104fa102f524b33823dc33c1defe2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:LZ2IRGANJNAEQKOCB6GUVYZQ6C","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:05:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vH+iwBmDIQlKdSoI9pmDplKKDj8jkMrbvTNHePrAenIRdT+HFdjmp647R7dDepKslBNICfKbfPtnQS1b1x2aDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T08:36:14.836203Z"},"content_sha256":"60be9f8d71c55dd78ded93536b6be84ffb37e521a4b93dd5f9c65abac077771b","schema_version":"1.0","event_id":"sha256:60be9f8d71c55dd78ded93536b6be84ffb37e521a4b93dd5f9c65abac077771b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LZ2IRGANJNAEQKOCB6GUVYZQ6C/bundle.json","state_url":"https://pith.science/pith/LZ2IRGANJNAEQKOCB6GUVYZQ6C/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LZ2IRGANJNAEQKOCB6GUVYZQ6C/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-27T08:36:14Z","links":{"resolver":"https://pith.science/pith/LZ2IRGANJNAEQKOCB6GUVYZQ6C","bundle":"https://pith.science/pith/LZ2IRGANJNAEQKOCB6GUVYZQ6C/bundle.json","state":"https://pith.science/pith/LZ2IRGANJNAEQKOCB6GUVYZQ6C/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LZ2IRGANJNAEQKOCB6GUVYZQ6C/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:LZ2IRGANJNAEQKOCB6GUVYZQ6C","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":"63a5730266373af09a6ab39434a77482ba062ff93b3422e68b6cebc56ec5aa14","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-21T09:17:09Z","title_canon_sha256":"89d3a4d0def796079131485ac9fe29df306e2b23478b05397e2f35b8b46ab28e"},"schema_version":"1.0","source":{"id":"1805.07956","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.07956","created_at":"2026-05-18T00:05:19Z"},{"alias_kind":"arxiv_version","alias_value":"1805.07956v2","created_at":"2026-05-18T00:05:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.07956","created_at":"2026-05-18T00:05:19Z"},{"alias_kind":"pith_short_12","alias_value":"LZ2IRGANJNAE","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"LZ2IRGANJNAEQKOC","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"LZ2IRGAN","created_at":"2026-05-18T12:32:37Z"}],"graph_snapshots":[{"event_id":"sha256:60be9f8d71c55dd78ded93536b6be84ffb37e521a4b93dd5f9c65abac077771b","target":"graph","created_at":"2026-05-18T00:05:19Z","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"},"paper":{"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","authors_text":"Bruno Scherrer, Gal Dalal, Shie Mannor, Yonathan Efroni","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-21T09:17:09Z","title":"Multiple-Step Greedy Policies in Online and Approximate Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.07956","kind":"arxiv","version":2},"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:bbaf82ea2eb58134ac0fafdbe186b4e8464104fa102f524b33823dc33c1defe2","target":"record","created_at":"2026-05-18T00:05:19Z","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":"63a5730266373af09a6ab39434a77482ba062ff93b3422e68b6cebc56ec5aa14","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-21T09:17:09Z","title_canon_sha256":"89d3a4d0def796079131485ac9fe29df306e2b23478b05397e2f35b8b46ab28e"},"schema_version":"1.0","source":{"id":"1805.07956","kind":"arxiv","version":2}},"canonical_sha256":"5e7488980d4b404829c20f8d4ae330f0a7e8152e04caa0c00f2e36f0ac8d5148","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5e7488980d4b404829c20f8d4ae330f0a7e8152e04caa0c00f2e36f0ac8d5148","first_computed_at":"2026-05-18T00:05:19.253327Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:05:19.253327Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZxDmm1EJy0jXijlonUGlU/84bKy06Wvrp8PyA5U4GoxHc5gPcduPNtMs3pch2mg2RXHVPEkand92XRgyV0nyBw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:05:19.253834Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.07956","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bbaf82ea2eb58134ac0fafdbe186b4e8464104fa102f524b33823dc33c1defe2","sha256:60be9f8d71c55dd78ded93536b6be84ffb37e521a4b93dd5f9c65abac077771b"],"state_sha256":"a707041b704806ea43933dfb8597f37329457654214fa1ce201b260a3de97693"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ai8cudCrBYjxCaV9lVJxlA23sTosVsQD1/70mO0vx9MkiUobsmWSwBjs+Hn5NuDtrgAvEzsNfby56blsQkYsDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T08:36:14.839451Z","bundle_sha256":"88380276704ebe9eef9b2a2265f5b129e5574547f997604a4a119c322cb4afdc"}}