{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2012:IRQ4NQ2AB6J3MKD4K2NXDJPTB3","short_pith_number":"pith:IRQ4NQ2A","schema_version":"1.0","canonical_sha256":"4461c6c3400f93b6287c569b71a5f30ee793aa51a99c4b7b12bb4b257a7c580b","source":{"kind":"arxiv","id":"1206.6870","version":1},"attestation_state":"computed","paper":{"title":"Incremental Model-based Learners With Formal Learning-Time Guarantees","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander L. Strehl, Lihong Li, Michael L. Littman","submitted_at":"2012-06-27T16:29:41Z","abstract_excerpt":"Model-based learning algorithms have been shown to use experience efficiently when learning to solve Markov Decision Processes (MDPs) with finite state and action spaces. However, their high computational cost due to repeatedly solving an internal model inhibits their use in large-scale problems. We propose a method based on real-time dynamic programming (RTDP) to speed up two model-based algorithms, RMAX and MBIE (model-based interval estimation), resulting in computationally much faster algorithms with little loss compared to existing bounds. Specifically, our two new learning algorithms, RT"},"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":"1206.6870","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-06-27T16:29:41Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"485c45d45e94d003e6ae29761a6ebf695f5cc566d2a75d0a05193d2636698fbc","abstract_canon_sha256":"e6dff8efdf8cba65859cd49fbc4d8dc9885a551f4f60de92ad8ccfc161762961"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:52:15.355256Z","signature_b64":"HaRyel1+X/FRNeHqpqgi41/ViBy04g+9UJM/wntQ+6ceXS67cOLmF7KmNYsOvPQTSRyE6KlhqxnCA1cIALYlBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4461c6c3400f93b6287c569b71a5f30ee793aa51a99c4b7b12bb4b257a7c580b","last_reissued_at":"2026-05-18T03:52:15.354653Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:52:15.354653Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Incremental Model-based Learners With Formal Learning-Time Guarantees","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander L. Strehl, Lihong Li, Michael L. Littman","submitted_at":"2012-06-27T16:29:41Z","abstract_excerpt":"Model-based learning algorithms have been shown to use experience efficiently when learning to solve Markov Decision Processes (MDPs) with finite state and action spaces. However, their high computational cost due to repeatedly solving an internal model inhibits their use in large-scale problems. We propose a method based on real-time dynamic programming (RTDP) to speed up two model-based algorithms, RMAX and MBIE (model-based interval estimation), resulting in computationally much faster algorithms with little loss compared to existing bounds. Specifically, our two new learning algorithms, RT"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1206.6870","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":"1206.6870","created_at":"2026-05-18T03:52:15.354755+00:00"},{"alias_kind":"arxiv_version","alias_value":"1206.6870v1","created_at":"2026-05-18T03:52:15.354755+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1206.6870","created_at":"2026-05-18T03:52:15.354755+00:00"},{"alias_kind":"pith_short_12","alias_value":"IRQ4NQ2AB6J3","created_at":"2026-05-18T12:27:09.501522+00:00"},{"alias_kind":"pith_short_16","alias_value":"IRQ4NQ2AB6J3MKD4","created_at":"2026-05-18T12:27:09.501522+00:00"},{"alias_kind":"pith_short_8","alias_value":"IRQ4NQ2A","created_at":"2026-05-18T12:27:09.501522+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/IRQ4NQ2AB6J3MKD4K2NXDJPTB3","json":"https://pith.science/pith/IRQ4NQ2AB6J3MKD4K2NXDJPTB3.json","graph_json":"https://pith.science/api/pith-number/IRQ4NQ2AB6J3MKD4K2NXDJPTB3/graph.json","events_json":"https://pith.science/api/pith-number/IRQ4NQ2AB6J3MKD4K2NXDJPTB3/events.json","paper":"https://pith.science/paper/IRQ4NQ2A"},"agent_actions":{"view_html":"https://pith.science/pith/IRQ4NQ2AB6J3MKD4K2NXDJPTB3","download_json":"https://pith.science/pith/IRQ4NQ2AB6J3MKD4K2NXDJPTB3.json","view_paper":"https://pith.science/paper/IRQ4NQ2A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1206.6870&json=true","fetch_graph":"https://pith.science/api/pith-number/IRQ4NQ2AB6J3MKD4K2NXDJPTB3/graph.json","fetch_events":"https://pith.science/api/pith-number/IRQ4NQ2AB6J3MKD4K2NXDJPTB3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IRQ4NQ2AB6J3MKD4K2NXDJPTB3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IRQ4NQ2AB6J3MKD4K2NXDJPTB3/action/storage_attestation","attest_author":"https://pith.science/pith/IRQ4NQ2AB6J3MKD4K2NXDJPTB3/action/author_attestation","sign_citation":"https://pith.science/pith/IRQ4NQ2AB6J3MKD4K2NXDJPTB3/action/citation_signature","submit_replication":"https://pith.science/pith/IRQ4NQ2AB6J3MKD4K2NXDJPTB3/action/replication_record"}},"created_at":"2026-05-18T03:52:15.354755+00:00","updated_at":"2026-05-18T03:52:15.354755+00:00"}