{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2012:IRQ4NQ2AB6J3MKD4K2NXDJPTB3","short_pith_number":"pith:IRQ4NQ2A","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"},"canonical_sha256":"4461c6c3400f93b6287c569b71a5f30ee793aa51a99c4b7b12bb4b257a7c580b","source":{"kind":"arxiv","id":"1206.6870","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1206.6870","created_at":"2026-05-18T03:52:15Z"},{"alias_kind":"arxiv_version","alias_value":"1206.6870v1","created_at":"2026-05-18T03:52:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1206.6870","created_at":"2026-05-18T03:52:15Z"},{"alias_kind":"pith_short_12","alias_value":"IRQ4NQ2AB6J3","created_at":"2026-05-18T12:27:09Z"},{"alias_kind":"pith_short_16","alias_value":"IRQ4NQ2AB6J3MKD4","created_at":"2026-05-18T12:27:09Z"},{"alias_kind":"pith_short_8","alias_value":"IRQ4NQ2A","created_at":"2026-05-18T12:27:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2012:IRQ4NQ2AB6J3MKD4K2NXDJPTB3","target":"record","payload":{"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"},"canonical_sha256":"4461c6c3400f93b6287c569b71a5f30ee793aa51a99c4b7b12bb4b257a7c580b","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"},"source_kind":"arxiv","source_id":"1206.6870","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":"2026-05-18T03:52:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"06yevpo8/cMVxUmvEYRVQ+PjOPsxvsiSgEA6M5TASkQ1bIaLteHkS7bv7caE94oBQ94jV99twWfYF8LviIjlAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T02:21:22.333035Z"},"content_sha256":"897ef4c1d65aaa30309ec018e90bc6d874cd72aa4d6475dfcd8a61ab6b1ea110","schema_version":"1.0","event_id":"sha256:897ef4c1d65aaa30309ec018e90bc6d874cd72aa4d6475dfcd8a61ab6b1ea110"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2012:IRQ4NQ2AB6J3MKD4K2NXDJPTB3","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:52:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JN1oGJD/coQsV4ti+5uDxtmBB72UsDjmtHiW42s/k1+zZU3r3dnDdKttitF3R2Z6ZdjVslvHaASSqIAO5XZ2Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T02:21:22.333816Z"},"content_sha256":"f30287487c75e74c36ea42e040afec273b38d38c35c38acfc05502492f17e0db","schema_version":"1.0","event_id":"sha256:f30287487c75e74c36ea42e040afec273b38d38c35c38acfc05502492f17e0db"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IRQ4NQ2AB6J3MKD4K2NXDJPTB3/bundle.json","state_url":"https://pith.science/pith/IRQ4NQ2AB6J3MKD4K2NXDJPTB3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IRQ4NQ2AB6J3MKD4K2NXDJPTB3/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":"2026-06-12T02:21:22Z","links":{"resolver":"https://pith.science/pith/IRQ4NQ2AB6J3MKD4K2NXDJPTB3","bundle":"https://pith.science/pith/IRQ4NQ2AB6J3MKD4K2NXDJPTB3/bundle.json","state":"https://pith.science/pith/IRQ4NQ2AB6J3MKD4K2NXDJPTB3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IRQ4NQ2AB6J3MKD4K2NXDJPTB3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:IRQ4NQ2AB6J3MKD4K2NXDJPTB3","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":"e6dff8efdf8cba65859cd49fbc4d8dc9885a551f4f60de92ad8ccfc161762961","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-06-27T16:29:41Z","title_canon_sha256":"485c45d45e94d003e6ae29761a6ebf695f5cc566d2a75d0a05193d2636698fbc"},"schema_version":"1.0","source":{"id":"1206.6870","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1206.6870","created_at":"2026-05-18T03:52:15Z"},{"alias_kind":"arxiv_version","alias_value":"1206.6870v1","created_at":"2026-05-18T03:52:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1206.6870","created_at":"2026-05-18T03:52:15Z"},{"alias_kind":"pith_short_12","alias_value":"IRQ4NQ2AB6J3","created_at":"2026-05-18T12:27:09Z"},{"alias_kind":"pith_short_16","alias_value":"IRQ4NQ2AB6J3MKD4","created_at":"2026-05-18T12:27:09Z"},{"alias_kind":"pith_short_8","alias_value":"IRQ4NQ2A","created_at":"2026-05-18T12:27:09Z"}],"graph_snapshots":[{"event_id":"sha256:f30287487c75e74c36ea42e040afec273b38d38c35c38acfc05502492f17e0db","target":"graph","created_at":"2026-05-18T03:52:15Z","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":"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","authors_text":"Alexander L. Strehl, Lihong Li, Michael L. Littman","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-06-27T16:29:41Z","title":"Incremental Model-based Learners With Formal Learning-Time Guarantees"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1206.6870","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":"sha256:897ef4c1d65aaa30309ec018e90bc6d874cd72aa4d6475dfcd8a61ab6b1ea110","target":"record","created_at":"2026-05-18T03:52:15Z","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":"e6dff8efdf8cba65859cd49fbc4d8dc9885a551f4f60de92ad8ccfc161762961","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-06-27T16:29:41Z","title_canon_sha256":"485c45d45e94d003e6ae29761a6ebf695f5cc566d2a75d0a05193d2636698fbc"},"schema_version":"1.0","source":{"id":"1206.6870","kind":"arxiv","version":1}},"canonical_sha256":"4461c6c3400f93b6287c569b71a5f30ee793aa51a99c4b7b12bb4b257a7c580b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4461c6c3400f93b6287c569b71a5f30ee793aa51a99c4b7b12bb4b257a7c580b","first_computed_at":"2026-05-18T03:52:15.354653Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:52:15.354653Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HaRyel1+X/FRNeHqpqgi41/ViBy04g+9UJM/wntQ+6ceXS67cOLmF7KmNYsOvPQTSRyE6KlhqxnCA1cIALYlBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T03:52:15.355256Z","signed_message":"canonical_sha256_bytes"},"source_id":"1206.6870","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:897ef4c1d65aaa30309ec018e90bc6d874cd72aa4d6475dfcd8a61ab6b1ea110","sha256:f30287487c75e74c36ea42e040afec273b38d38c35c38acfc05502492f17e0db"],"state_sha256":"506533e48bc5e37e74f2280e639159a363937a50359e8bdb342e056c3c9c62d3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6/FYoWBJ2v4v5S4yAu1FDnEECnTmweDboR7r6gwdVPbGo2evjomELphKBBU+mBkraLp/bZuj0zXEA3g0NbZKDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-12T02:21:22.338039Z","bundle_sha256":"d6420bf4bc7eed4a2e8264a7d79bbe958af966098a026ec9b44ae9f3d114ba14"}}