{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:B72AE4AQ56LW2YKWLBD2DUSING","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":"de98d242358dfa08b95b90917b7fb78ff705410a7564478f4c7613a178163305","cross_cats_sorted":["cs.AI","cs.FL","cs.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SY","submitted_at":"2021-09-27T22:44:55Z","title_canon_sha256":"73b7dfc1c9d0afe5670a5b98f9b4f8a0dfdb7835b4232ec972c6183566cef20f"},"schema_version":"1.0","source":{"id":"2109.13377","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.13377","created_at":"2026-07-05T03:18:02Z"},{"alias_kind":"arxiv_version","alias_value":"2109.13377v1","created_at":"2026-07-05T03:18:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.13377","created_at":"2026-07-05T03:18:02Z"},{"alias_kind":"pith_short_12","alias_value":"B72AE4AQ56LW","created_at":"2026-07-05T03:18:02Z"},{"alias_kind":"pith_short_16","alias_value":"B72AE4AQ56LW2YKW","created_at":"2026-07-05T03:18:02Z"},{"alias_kind":"pith_short_8","alias_value":"B72AE4AQ","created_at":"2026-07-05T03:18:02Z"}],"graph_snapshots":[{"event_id":"sha256:537043f42366441c6c164c7a3ea038d0e8ff7847296f45054d98f494b7d458e2","target":"graph","created_at":"2026-07-05T03:18:02Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2109.13377/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a model-free reinforcement learning algorithm to find an optimal policy for a finite-horizon Markov decision process while guaranteeing a desired lower bound on the probability of satisfying a signal temporal logic (STL) specification. We propose a method to effectively augment the MDP state space to capture the required state history and express the STL objective as a reachability objective. The planning problem can then be formulated as a finite-horizon constrained Markov decision process (CMDP). For a general finite horizon CMDP problem with unknown transition probability, we dev","authors_text":"Krishna C. Kalagarla, Pierluigi Nuzzo, Rahul Jain","cross_cats":["cs.AI","cs.FL","cs.SY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SY","submitted_at":"2021-09-27T22:44:55Z","title":"Model-Free Reinforcement Learning for Optimal Control of MarkovDecision Processes Under Signal Temporal Logic Specifications"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.13377","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:a8f1dd74718ef2916757967a022a4e61661a8d05b902eb1ac05e6a48fa72a58e","target":"record","created_at":"2026-07-05T03:18:02Z","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":"de98d242358dfa08b95b90917b7fb78ff705410a7564478f4c7613a178163305","cross_cats_sorted":["cs.AI","cs.FL","cs.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SY","submitted_at":"2021-09-27T22:44:55Z","title_canon_sha256":"73b7dfc1c9d0afe5670a5b98f9b4f8a0dfdb7835b4232ec972c6183566cef20f"},"schema_version":"1.0","source":{"id":"2109.13377","kind":"arxiv","version":1}},"canonical_sha256":"0ff4027010ef976d61565847a1d24869ac53f0bf935ae167421a1ab3be4e8b98","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0ff4027010ef976d61565847a1d24869ac53f0bf935ae167421a1ab3be4e8b98","first_computed_at":"2026-07-05T03:18:02.093699Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:18:02.093699Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eVINRXCTbdYyugClZaT70JpwS0UgXjww3ZfBsV20etVTLffnZmU0Lg+BKDLddJNezuRu3SyCzrXMRlt4Bn9hBA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:18:02.094213Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.13377","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a8f1dd74718ef2916757967a022a4e61661a8d05b902eb1ac05e6a48fa72a58e","sha256:537043f42366441c6c164c7a3ea038d0e8ff7847296f45054d98f494b7d458e2"],"state_sha256":"e65a2482a497aa821a291893d5eb4dc757ba630bbf8a0954f7d98fcab2c0f983"}