{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:BMXTDUGKHFNLVROHT6YWFLVU56","short_pith_number":"pith:BMXTDUGK","canonical_record":{"source":{"id":"1904.04700","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-09T14:29:53Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7f910bdfba1ddb7a3718de1aace6639d6d871245028256cd4de23e3c5f3d1443","abstract_canon_sha256":"c7bc74ab911ea2fcbcae6875cd31b8775f8a97a845b01dfd6002c16f6b75d780"},"schema_version":"1.0"},"canonical_sha256":"0b2f31d0ca395abac5c79fb162aeb4efa98f7ce232d292b4dc426742036020cb","source":{"kind":"arxiv","id":"1904.04700","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.04700","created_at":"2026-05-17T23:48:58Z"},{"alias_kind":"arxiv_version","alias_value":"1904.04700v1","created_at":"2026-05-17T23:48:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.04700","created_at":"2026-05-17T23:48:58Z"},{"alias_kind":"pith_short_12","alias_value":"BMXTDUGKHFNL","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"BMXTDUGKHFNLVROH","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"BMXTDUGK","created_at":"2026-05-18T12:33:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:BMXTDUGKHFNLVROHT6YWFLVU56","target":"record","payload":{"canonical_record":{"source":{"id":"1904.04700","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-09T14:29:53Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"7f910bdfba1ddb7a3718de1aace6639d6d871245028256cd4de23e3c5f3d1443","abstract_canon_sha256":"c7bc74ab911ea2fcbcae6875cd31b8775f8a97a845b01dfd6002c16f6b75d780"},"schema_version":"1.0"},"canonical_sha256":"0b2f31d0ca395abac5c79fb162aeb4efa98f7ce232d292b4dc426742036020cb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:48:58.370875Z","signature_b64":"OOJsRPWCg3/d06cK/mx/oip9Q1ym2G41bZ7rIWWGKvIQPxVtm1eYZs3dfsj7lD13w2gOH9xDj9DSIaqhzcgvBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0b2f31d0ca395abac5c79fb162aeb4efa98f7ce232d292b4dc426742036020cb","last_reissued_at":"2026-05-17T23:48:58.370372Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:48:58.370372Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1904.04700","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:48:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X4zVy9uU3H/VgWfJ4fGV9Olf6Tz++O/UvDB3bm42O3+K8ZQsCGC9S2fF9ulnQheM1bHGA/13wTEEtFNsrmYBDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T15:28:50.506968Z"},"content_sha256":"934b365a0bf87a5d3052945bc836fc0abd081de8859d84c7b13225a134f0255a","schema_version":"1.0","event_id":"sha256:934b365a0bf87a5d3052945bc836fc0abd081de8859d84c7b13225a134f0255a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:BMXTDUGKHFNLVROHT6YWFLVU56","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Practical Open-Loop Optimistic Planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Edouard Leurent, Odalric-Ambrym Maillard","submitted_at":"2019-04-09T14:29:53Z","abstract_excerpt":"We consider the problem of online planning in a Markov Decision Process when given only access to a generative model, restricted to open-loop policies - i.e. sequences of actions - and under budget constraint. In this setting, the Open-Loop Optimistic Planning (OLOP) algorithm enjoys good theoretical guarantees but is overly conservative in practice, as we show in numerical experiments. We propose a modified version of the algorithm with tighter upper-confidence bounds, KLOLOP, that leads to better practical performances while retaining the sample complexity bound. Finally, we propose an effic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.04700","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":""},"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":"2026-05-17T23:48:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xkEGMNzkrXyAoFB9x9TY2rAhffSUXCyxygdx8BZn50DI1/s0qEM32uLbv55J82lruYlHuXMJmFdzo2ot+wmRAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T15:28:50.507618Z"},"content_sha256":"67d5c3fdaf4da4953b1911e940c98b51fbe4a8b77685165c4818d299a1294277","schema_version":"1.0","event_id":"sha256:67d5c3fdaf4da4953b1911e940c98b51fbe4a8b77685165c4818d299a1294277"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BMXTDUGKHFNLVROHT6YWFLVU56/bundle.json","state_url":"https://pith.science/pith/BMXTDUGKHFNLVROHT6YWFLVU56/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BMXTDUGKHFNLVROHT6YWFLVU56/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":"2026-05-22T15:28:50Z","links":{"resolver":"https://pith.science/pith/BMXTDUGKHFNLVROHT6YWFLVU56","bundle":"https://pith.science/pith/BMXTDUGKHFNLVROHT6YWFLVU56/bundle.json","state":"https://pith.science/pith/BMXTDUGKHFNLVROHT6YWFLVU56/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BMXTDUGKHFNLVROHT6YWFLVU56/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:BMXTDUGKHFNLVROHT6YWFLVU56","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":"c7bc74ab911ea2fcbcae6875cd31b8775f8a97a845b01dfd6002c16f6b75d780","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-09T14:29:53Z","title_canon_sha256":"7f910bdfba1ddb7a3718de1aace6639d6d871245028256cd4de23e3c5f3d1443"},"schema_version":"1.0","source":{"id":"1904.04700","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.04700","created_at":"2026-05-17T23:48:58Z"},{"alias_kind":"arxiv_version","alias_value":"1904.04700v1","created_at":"2026-05-17T23:48:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.04700","created_at":"2026-05-17T23:48:58Z"},{"alias_kind":"pith_short_12","alias_value":"BMXTDUGKHFNL","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"BMXTDUGKHFNLVROH","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"BMXTDUGK","created_at":"2026-05-18T12:33:12Z"}],"graph_snapshots":[{"event_id":"sha256:67d5c3fdaf4da4953b1911e940c98b51fbe4a8b77685165c4818d299a1294277","target":"graph","created_at":"2026-05-17T23:48:58Z","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":"We consider the problem of online planning in a Markov Decision Process when given only access to a generative model, restricted to open-loop policies - i.e. sequences of actions - and under budget constraint. In this setting, the Open-Loop Optimistic Planning (OLOP) algorithm enjoys good theoretical guarantees but is overly conservative in practice, as we show in numerical experiments. We propose a modified version of the algorithm with tighter upper-confidence bounds, KLOLOP, that leads to better practical performances while retaining the sample complexity bound. Finally, we propose an effic","authors_text":"Edouard Leurent, Odalric-Ambrym Maillard","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-09T14:29:53Z","title":"Practical Open-Loop Optimistic Planning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.04700","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":"sha256:934b365a0bf87a5d3052945bc836fc0abd081de8859d84c7b13225a134f0255a","target":"record","created_at":"2026-05-17T23:48:58Z","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":"c7bc74ab911ea2fcbcae6875cd31b8775f8a97a845b01dfd6002c16f6b75d780","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-09T14:29:53Z","title_canon_sha256":"7f910bdfba1ddb7a3718de1aace6639d6d871245028256cd4de23e3c5f3d1443"},"schema_version":"1.0","source":{"id":"1904.04700","kind":"arxiv","version":1}},"canonical_sha256":"0b2f31d0ca395abac5c79fb162aeb4efa98f7ce232d292b4dc426742036020cb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0b2f31d0ca395abac5c79fb162aeb4efa98f7ce232d292b4dc426742036020cb","first_computed_at":"2026-05-17T23:48:58.370372Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:48:58.370372Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OOJsRPWCg3/d06cK/mx/oip9Q1ym2G41bZ7rIWWGKvIQPxVtm1eYZs3dfsj7lD13w2gOH9xDj9DSIaqhzcgvBQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:48:58.370875Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.04700","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:934b365a0bf87a5d3052945bc836fc0abd081de8859d84c7b13225a134f0255a","sha256:67d5c3fdaf4da4953b1911e940c98b51fbe4a8b77685165c4818d299a1294277"],"state_sha256":"464d61a80d77f061f0f877fc40fc191803532eb93463cfd1e7612b25fd9b37c5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WMNCSpvML6O9LGNc4djuQo13FCe9FIIeOSi81W1c8MaYb6D414v4s7dY2+GxttAJWjG+jsXgxDVz7amx3ehaAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-22T15:28:50.511029Z","bundle_sha256":"60c80352fa139ed99c93abe063c432ff8820f575008f57d4148347373569c920"}}