{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:2VQFWYYA6CMSC7QWWN5OBM4CLD","short_pith_number":"pith:2VQFWYYA","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"},"canonical_sha256":"d5605b6300f099217e16b37ae0b38258cbcaeb2be17b6651e18f4cee8db030d5","source":{"kind":"arxiv","id":"1810.00950","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.00950","created_at":"2026-05-18T00:04:19Z"},{"alias_kind":"arxiv_version","alias_value":"1810.00950v1","created_at":"2026-05-18T00:04:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.00950","created_at":"2026-05-18T00:04:19Z"},{"alias_kind":"pith_short_12","alias_value":"2VQFWYYA6CMS","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"2VQFWYYA6CMSC7QW","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"2VQFWYYA","created_at":"2026-05-18T12:32:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:2VQFWYYA6CMSC7QWWN5OBM4CLD","target":"record","payload":{"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"},"canonical_sha256":"d5605b6300f099217e16b37ae0b38258cbcaeb2be17b6651e18f4cee8db030d5","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"},"source_kind":"arxiv","source_id":"1810.00950","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":"2026-05-18T00:04:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ItsCTJNbLQTlZ2Hn3KCMdKWjYm39uXECkne0J+qq8jiAaZSpoNai2nIXsKyFZUN9LbQ5M/xMd52DGsX3vomvBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T21:12:19.553547Z"},"content_sha256":"70b8e5229819d81c576d1d02afc6d795ad4dbbf0236efb498df7a2fe7d5d6e07","schema_version":"1.0","event_id":"sha256:70b8e5229819d81c576d1d02afc6d795ad4dbbf0236efb498df7a2fe7d5d6e07"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:2VQFWYYA6CMSC7QWWN5OBM4CLD","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:04:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RXNylysP2m+R3l8qM5MxHGC01oZLuF3Tg/HA15rANrcNBcXUqF+39dpERJVHvbwgqUuRQYp4lWhkaEj/lD8vAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T21:12:19.554239Z"},"content_sha256":"e1ee8ccf40729fead087b9241ae3a312b27e072e806c68ac4064db1528ee1847","schema_version":"1.0","event_id":"sha256:e1ee8ccf40729fead087b9241ae3a312b27e072e806c68ac4064db1528ee1847"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2VQFWYYA6CMSC7QWWN5OBM4CLD/bundle.json","state_url":"https://pith.science/pith/2VQFWYYA6CMSC7QWWN5OBM4CLD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2VQFWYYA6CMSC7QWWN5OBM4CLD/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":"2026-05-29T21:12:19Z","links":{"resolver":"https://pith.science/pith/2VQFWYYA6CMSC7QWWN5OBM4CLD","bundle":"https://pith.science/pith/2VQFWYYA6CMSC7QWWN5OBM4CLD/bundle.json","state":"https://pith.science/pith/2VQFWYYA6CMSC7QWWN5OBM4CLD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2VQFWYYA6CMSC7QWWN5OBM4CLD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:2VQFWYYA6CMSC7QWWN5OBM4CLD","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":"7a4e672c80ae9cd9ac3fd2c6e8a468ff4dfac4595fbe4cd6c381f1d6d4b2e9ff","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LO","submitted_at":"2018-09-26T18:04:56Z","title_canon_sha256":"c82be01f8afadd9af85f64145bc2bd50a1f8a28efb5090a950288d047c5f7696"},"schema_version":"1.0","source":{"id":"1810.00950","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.00950","created_at":"2026-05-18T00:04:19Z"},{"alias_kind":"arxiv_version","alias_value":"1810.00950v1","created_at":"2026-05-18T00:04:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.00950","created_at":"2026-05-18T00:04:19Z"},{"alias_kind":"pith_short_12","alias_value":"2VQFWYYA6CMS","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"2VQFWYYA6CMSC7QW","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"2VQFWYYA","created_at":"2026-05-18T12:32:02Z"}],"graph_snapshots":[{"event_id":"sha256:e1ee8ccf40729fead087b9241ae3a312b27e072e806c68ac4064db1528ee1847","target":"graph","created_at":"2026-05-18T00:04:19Z","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":"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","authors_text":"Ashutosh Trivedi, Dominik Wojtczak, Ernst Moritz Hahn, Fabio Somenzi, Mateo Perez, Sven Schewe","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LO","submitted_at":"2018-09-26T18:04:56Z","title":"Omega-Regular Objectives in Model-Free Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.00950","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":"sha256:70b8e5229819d81c576d1d02afc6d795ad4dbbf0236efb498df7a2fe7d5d6e07","target":"record","created_at":"2026-05-18T00:04:19Z","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":"7a4e672c80ae9cd9ac3fd2c6e8a468ff4dfac4595fbe4cd6c381f1d6d4b2e9ff","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LO","submitted_at":"2018-09-26T18:04:56Z","title_canon_sha256":"c82be01f8afadd9af85f64145bc2bd50a1f8a28efb5090a950288d047c5f7696"},"schema_version":"1.0","source":{"id":"1810.00950","kind":"arxiv","version":1}},"canonical_sha256":"d5605b6300f099217e16b37ae0b38258cbcaeb2be17b6651e18f4cee8db030d5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d5605b6300f099217e16b37ae0b38258cbcaeb2be17b6651e18f4cee8db030d5","first_computed_at":"2026-05-18T00:04:19.477268Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:04:19.477268Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mlG9AmFXeoqV183i9dI3NBleiBCRWOOsR8oT8N2W/1/qTmQiXnXjtWLithWHO59vDiOCYmKQtINZvdMzbg9SDw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:04:19.477758Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.00950","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:70b8e5229819d81c576d1d02afc6d795ad4dbbf0236efb498df7a2fe7d5d6e07","sha256:e1ee8ccf40729fead087b9241ae3a312b27e072e806c68ac4064db1528ee1847"],"state_sha256":"6803bb5d499ce83feba2c07556b929db4d207ddb661c662305f306c930305add"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KnfPJaU3+z7vGUp7s6ol8TpVYUSnpMHeWAhfJOUa4KIlANNcY5pb5WAJw6AtpjvXZ6vhQ+FeMFCFdudjvc3LBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-29T21:12:19.557727Z","bundle_sha256":"cec10170882750a3cb242c5cca0f18ededddd5c23e1ec1a11e547a94a2a3d5cf"}}