{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:BMXTDUGKHFNLVROHT6YWFLVU56","short_pith_number":"pith:BMXTDUGK","schema_version":"1.0","canonical_sha256":"0b2f31d0ca395abac5c79fb162aeb4efa98f7ce232d292b4dc426742036020cb","source":{"kind":"arxiv","id":"1904.04700","version":1},"attestation_state":"computed","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"},"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":"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1904.04700","created_at":"2026-05-17T23:48:58.370436+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.04700v1","created_at":"2026-05-17T23:48:58.370436+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.04700","created_at":"2026-05-17T23:48:58.370436+00:00"},{"alias_kind":"pith_short_12","alias_value":"BMXTDUGKHFNL","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_16","alias_value":"BMXTDUGKHFNLVROH","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_8","alias_value":"BMXTDUGK","created_at":"2026-05-18T12:33:12.712433+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.18312","citing_title":"Scale-free adaptive planning for deterministic dynamics & discounted rewards","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19695","citing_title":"Planning in entropy-regularized Markov decision processes and games","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BMXTDUGKHFNLVROHT6YWFLVU56","json":"https://pith.science/pith/BMXTDUGKHFNLVROHT6YWFLVU56.json","graph_json":"https://pith.science/api/pith-number/BMXTDUGKHFNLVROHT6YWFLVU56/graph.json","events_json":"https://pith.science/api/pith-number/BMXTDUGKHFNLVROHT6YWFLVU56/events.json","paper":"https://pith.science/paper/BMXTDUGK"},"agent_actions":{"view_html":"https://pith.science/pith/BMXTDUGKHFNLVROHT6YWFLVU56","download_json":"https://pith.science/pith/BMXTDUGKHFNLVROHT6YWFLVU56.json","view_paper":"https://pith.science/paper/BMXTDUGK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.04700&json=true","fetch_graph":"https://pith.science/api/pith-number/BMXTDUGKHFNLVROHT6YWFLVU56/graph.json","fetch_events":"https://pith.science/api/pith-number/BMXTDUGKHFNLVROHT6YWFLVU56/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BMXTDUGKHFNLVROHT6YWFLVU56/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BMXTDUGKHFNLVROHT6YWFLVU56/action/storage_attestation","attest_author":"https://pith.science/pith/BMXTDUGKHFNLVROHT6YWFLVU56/action/author_attestation","sign_citation":"https://pith.science/pith/BMXTDUGKHFNLVROHT6YWFLVU56/action/citation_signature","submit_replication":"https://pith.science/pith/BMXTDUGKHFNLVROHT6YWFLVU56/action/replication_record"}},"created_at":"2026-05-17T23:48:58.370436+00:00","updated_at":"2026-05-17T23:48:58.370436+00:00"}