{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:2VQFWYYA6CMSC7QWWN5OBM4CLD","short_pith_number":"pith:2VQFWYYA","schema_version":"1.0","canonical_sha256":"d5605b6300f099217e16b37ae0b38258cbcaeb2be17b6651e18f4cee8db030d5","source":{"kind":"arxiv","id":"1810.00950","version":1},"attestation_state":"computed","paper":{"title":"Omega-Regular Objectives in Model-Free Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.LO","authors_text":"Ashutosh Trivedi, Dominik Wojtczak, Ernst Moritz Hahn, Fabio Somenzi, Mateo Perez, Sven Schewe","submitted_at":"2018-09-26T18:04:56Z","abstract_excerpt":"We provide the first solution for model-free reinforcement learning of {\\omega}-regular objectives for Markov decision processes (MDPs). We present a constructive reduction from the almost-sure satisfaction of {\\omega}-regular objectives to an almost- sure reachability problem and extend this technique to learning how to control an unknown model so that the chance of satisfying the objective is maximized. A key feature of our technique is the compilation of {\\omega}-regular properties into limit- deterministic Buechi automata instead of the traditional Rabin automata; this choice sidesteps dif"},"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":"1810.00950","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LO","submitted_at":"2018-09-26T18:04:56Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"c82be01f8afadd9af85f64145bc2bd50a1f8a28efb5090a950288d047c5f7696","abstract_canon_sha256":"7a4e672c80ae9cd9ac3fd2c6e8a468ff4dfac4595fbe4cd6c381f1d6d4b2e9ff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:04:19.477758Z","signature_b64":"mlG9AmFXeoqV183i9dI3NBleiBCRWOOsR8oT8N2W/1/qTmQiXnXjtWLithWHO59vDiOCYmKQtINZvdMzbg9SDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d5605b6300f099217e16b37ae0b38258cbcaeb2be17b6651e18f4cee8db030d5","last_reissued_at":"2026-05-18T00:04:19.477268Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:04:19.477268Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Omega-Regular Objectives in Model-Free Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.LO","authors_text":"Ashutosh Trivedi, Dominik Wojtczak, Ernst Moritz Hahn, Fabio Somenzi, Mateo Perez, Sven Schewe","submitted_at":"2018-09-26T18:04:56Z","abstract_excerpt":"We provide the first solution for model-free reinforcement learning of {\\omega}-regular objectives for Markov decision processes (MDPs). We present a constructive reduction from the almost-sure satisfaction of {\\omega}-regular objectives to an almost- sure reachability problem and extend this technique to learning how to control an unknown model so that the chance of satisfying the objective is maximized. A key feature of our technique is the compilation of {\\omega}-regular properties into limit- deterministic Buechi automata instead of the traditional Rabin automata; this choice sidesteps dif"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.00950","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":"1810.00950","created_at":"2026-05-18T00:04:19.477357+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.00950v1","created_at":"2026-05-18T00:04:19.477357+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.00950","created_at":"2026-05-18T00:04:19.477357+00:00"},{"alias_kind":"pith_short_12","alias_value":"2VQFWYYA6CMS","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_16","alias_value":"2VQFWYYA6CMSC7QW","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_8","alias_value":"2VQFWYYA","created_at":"2026-05-18T12:32:02.567920+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/2VQFWYYA6CMSC7QWWN5OBM4CLD","json":"https://pith.science/pith/2VQFWYYA6CMSC7QWWN5OBM4CLD.json","graph_json":"https://pith.science/api/pith-number/2VQFWYYA6CMSC7QWWN5OBM4CLD/graph.json","events_json":"https://pith.science/api/pith-number/2VQFWYYA6CMSC7QWWN5OBM4CLD/events.json","paper":"https://pith.science/paper/2VQFWYYA"},"agent_actions":{"view_html":"https://pith.science/pith/2VQFWYYA6CMSC7QWWN5OBM4CLD","download_json":"https://pith.science/pith/2VQFWYYA6CMSC7QWWN5OBM4CLD.json","view_paper":"https://pith.science/paper/2VQFWYYA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.00950&json=true","fetch_graph":"https://pith.science/api/pith-number/2VQFWYYA6CMSC7QWWN5OBM4CLD/graph.json","fetch_events":"https://pith.science/api/pith-number/2VQFWYYA6CMSC7QWWN5OBM4CLD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2VQFWYYA6CMSC7QWWN5OBM4CLD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2VQFWYYA6CMSC7QWWN5OBM4CLD/action/storage_attestation","attest_author":"https://pith.science/pith/2VQFWYYA6CMSC7QWWN5OBM4CLD/action/author_attestation","sign_citation":"https://pith.science/pith/2VQFWYYA6CMSC7QWWN5OBM4CLD/action/citation_signature","submit_replication":"https://pith.science/pith/2VQFWYYA6CMSC7QWWN5OBM4CLD/action/replication_record"}},"created_at":"2026-05-18T00:04:19.477357+00:00","updated_at":"2026-05-18T00:04:19.477357+00:00"}