{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:6UEWJ6PYECZDRBS2WVR42ZXKMF","short_pith_number":"pith:6UEWJ6PY","schema_version":"1.0","canonical_sha256":"f50964f9f820b238865ab563cd66ea614b4b0eb89d812a271ee413fa835f34ef","source":{"kind":"arxiv","id":"1807.02373","version":2},"attestation_state":"computed","paper":{"title":"Near Optimal Exploration-Exploitation in Non-Communicating Markov Decision Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alessandro Lazaric, Matteo Pirotta, Ronan Fruit","submitted_at":"2018-07-06T12:13:52Z","abstract_excerpt":"While designing the state space of an MDP, it is common to include states that are transient or not reachable by any policy (e.g., in mountain car, the product space of speed and position contains configurations that are not physically reachable). This leads to defining weakly-communicating or multi-chain MDPs. In this paper, we introduce \\tucrl, the first algorithm able to perform efficient exploration-exploitation in any finite Markov Decision Process (MDP) without requiring any form of prior knowledge. In particular, for any MDP with $S^{\\texttt{C}}$ communicating states, $A$ actions and $\\"},"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":"1807.02373","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-06T12:13:52Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"13a22f7377f7e9cc2759b64874e55b7de551a11141f4cbdc52af0b4b51812456","abstract_canon_sha256":"c9eea4ad38220a651b5fec71593e891fe4ad6ea8ec3dcd6d9f36ba91c347a370"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:50:49.099808Z","signature_b64":"L2GzmbsVhAaXxo1mOXqLS2zSktqYvur2HtsjtxCOh5ad8A8xTKHvPglaIGdQHQ9OjN7PI1DOZUkAbKQcXaxDAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f50964f9f820b238865ab563cd66ea614b4b0eb89d812a271ee413fa835f34ef","last_reissued_at":"2026-05-17T23:50:49.099149Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:50:49.099149Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Near Optimal Exploration-Exploitation in Non-Communicating Markov Decision Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alessandro Lazaric, Matteo Pirotta, Ronan Fruit","submitted_at":"2018-07-06T12:13:52Z","abstract_excerpt":"While designing the state space of an MDP, it is common to include states that are transient or not reachable by any policy (e.g., in mountain car, the product space of speed and position contains configurations that are not physically reachable). This leads to defining weakly-communicating or multi-chain MDPs. In this paper, we introduce \\tucrl, the first algorithm able to perform efficient exploration-exploitation in any finite Markov Decision Process (MDP) without requiring any form of prior knowledge. In particular, for any MDP with $S^{\\texttt{C}}$ communicating states, $A$ actions and $\\"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.02373","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":""},"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":"1807.02373","created_at":"2026-05-17T23:50:49.099246+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.02373v2","created_at":"2026-05-17T23:50:49.099246+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.02373","created_at":"2026-05-17T23:50:49.099246+00:00"},{"alias_kind":"pith_short_12","alias_value":"6UEWJ6PYECZD","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_16","alias_value":"6UEWJ6PYECZDRBS2","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_8","alias_value":"6UEWJ6PY","created_at":"2026-05-18T12:32:11.075285+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/6UEWJ6PYECZDRBS2WVR42ZXKMF","json":"https://pith.science/pith/6UEWJ6PYECZDRBS2WVR42ZXKMF.json","graph_json":"https://pith.science/api/pith-number/6UEWJ6PYECZDRBS2WVR42ZXKMF/graph.json","events_json":"https://pith.science/api/pith-number/6UEWJ6PYECZDRBS2WVR42ZXKMF/events.json","paper":"https://pith.science/paper/6UEWJ6PY"},"agent_actions":{"view_html":"https://pith.science/pith/6UEWJ6PYECZDRBS2WVR42ZXKMF","download_json":"https://pith.science/pith/6UEWJ6PYECZDRBS2WVR42ZXKMF.json","view_paper":"https://pith.science/paper/6UEWJ6PY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.02373&json=true","fetch_graph":"https://pith.science/api/pith-number/6UEWJ6PYECZDRBS2WVR42ZXKMF/graph.json","fetch_events":"https://pith.science/api/pith-number/6UEWJ6PYECZDRBS2WVR42ZXKMF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6UEWJ6PYECZDRBS2WVR42ZXKMF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6UEWJ6PYECZDRBS2WVR42ZXKMF/action/storage_attestation","attest_author":"https://pith.science/pith/6UEWJ6PYECZDRBS2WVR42ZXKMF/action/author_attestation","sign_citation":"https://pith.science/pith/6UEWJ6PYECZDRBS2WVR42ZXKMF/action/citation_signature","submit_replication":"https://pith.science/pith/6UEWJ6PYECZDRBS2WVR42ZXKMF/action/replication_record"}},"created_at":"2026-05-17T23:50:49.099246+00:00","updated_at":"2026-05-17T23:50:49.099246+00:00"}