{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:PDOBNMOPYOLY6OLP566CVPOKJO","short_pith_number":"pith:PDOBNMOP","schema_version":"1.0","canonical_sha256":"78dc16b1cfc3978f396fefbc2abdca4b9ec79573e81615a8d3c63dbe4c44300e","source":{"kind":"arxiv","id":"2003.03297","version":2},"attestation_state":"computed","paper":{"title":"Active Model Estimation in Markov Decision Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alessandro Lazaric, Jean Tarbouriech, Matteo Pirotta, Mohammad Ghavamzadeh, Shubhanshu Shekhar","submitted_at":"2020-03-06T16:17:24Z","abstract_excerpt":"We study the problem of efficient exploration in order to learn an accurate model of an environment, modeled as a Markov decision process (MDP). Efficient exploration in this problem requires the agent to identify the regions in which estimating the model is more difficult and then exploit this knowledge to collect more samples there. In this paper, we formalize this problem, introduce the first algorithm to learn an $\\epsilon$-accurate estimate of the dynamics, and provide its sample complexity analysis. While this algorithm enjoys strong guarantees in the large-sample regime, it tends to hav"},"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":"2003.03297","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-03-06T16:17:24Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4c1a5e069e2dcb180f83c1a9f53865e0ebdc760b657e4f3b1889825197d2053f","abstract_canon_sha256":"ae63aaf4b6c699f24f23704dc7ed6e7559945467e5a9a5897a17fe2827368d45"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:12:02.757841Z","signature_b64":"aOyPb7G7aJghguJH0r5X5eNHL8YpX+Dzr/yFzLSWX/5rE3c8uAPrkeNMmR55CY4o/fIBaAefPTK7qnsbNZ7aBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78dc16b1cfc3978f396fefbc2abdca4b9ec79573e81615a8d3c63dbe4c44300e","last_reissued_at":"2026-07-05T01:12:02.757357Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:12:02.757357Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Active Model Estimation in Markov Decision Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alessandro Lazaric, Jean Tarbouriech, Matteo Pirotta, Mohammad Ghavamzadeh, Shubhanshu Shekhar","submitted_at":"2020-03-06T16:17:24Z","abstract_excerpt":"We study the problem of efficient exploration in order to learn an accurate model of an environment, modeled as a Markov decision process (MDP). Efficient exploration in this problem requires the agent to identify the regions in which estimating the model is more difficult and then exploit this knowledge to collect more samples there. In this paper, we formalize this problem, introduce the first algorithm to learn an $\\epsilon$-accurate estimate of the dynamics, and provide its sample complexity analysis. While this algorithm enjoys strong guarantees in the large-sample regime, it tends to hav"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.03297","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2003.03297/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2003.03297","created_at":"2026-07-05T01:12:02.757417+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.03297v2","created_at":"2026-07-05T01:12:02.757417+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.03297","created_at":"2026-07-05T01:12:02.757417+00:00"},{"alias_kind":"pith_short_12","alias_value":"PDOBNMOPYOLY","created_at":"2026-07-05T01:12:02.757417+00:00"},{"alias_kind":"pith_short_16","alias_value":"PDOBNMOPYOLY6OLP","created_at":"2026-07-05T01:12:02.757417+00:00"},{"alias_kind":"pith_short_8","alias_value":"PDOBNMOP","created_at":"2026-07-05T01:12:02.757417+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/PDOBNMOPYOLY6OLP566CVPOKJO","json":"https://pith.science/pith/PDOBNMOPYOLY6OLP566CVPOKJO.json","graph_json":"https://pith.science/api/pith-number/PDOBNMOPYOLY6OLP566CVPOKJO/graph.json","events_json":"https://pith.science/api/pith-number/PDOBNMOPYOLY6OLP566CVPOKJO/events.json","paper":"https://pith.science/paper/PDOBNMOP"},"agent_actions":{"view_html":"https://pith.science/pith/PDOBNMOPYOLY6OLP566CVPOKJO","download_json":"https://pith.science/pith/PDOBNMOPYOLY6OLP566CVPOKJO.json","view_paper":"https://pith.science/paper/PDOBNMOP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.03297&json=true","fetch_graph":"https://pith.science/api/pith-number/PDOBNMOPYOLY6OLP566CVPOKJO/graph.json","fetch_events":"https://pith.science/api/pith-number/PDOBNMOPYOLY6OLP566CVPOKJO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PDOBNMOPYOLY6OLP566CVPOKJO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PDOBNMOPYOLY6OLP566CVPOKJO/action/storage_attestation","attest_author":"https://pith.science/pith/PDOBNMOPYOLY6OLP566CVPOKJO/action/author_attestation","sign_citation":"https://pith.science/pith/PDOBNMOPYOLY6OLP566CVPOKJO/action/citation_signature","submit_replication":"https://pith.science/pith/PDOBNMOPYOLY6OLP566CVPOKJO/action/replication_record"}},"created_at":"2026-07-05T01:12:02.757417+00:00","updated_at":"2026-07-05T01:12:02.757417+00:00"}