{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:XKKMOSBACORT3AFMDKZ5EMC42I","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":"5f899a86e6f5731816258759b63f21b00caeaaa16aa43366f255642b078e84be","cross_cats_sorted":["cs.AI","cs.RO","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.FL","submitted_at":"2020-10-14T03:49:16Z","title_canon_sha256":"2b2d25bd8c4990c0f1f8d98774070468bc2cdf5f5496823efafa5e3f09075289"},"schema_version":"1.0","source":{"id":"2010.06797","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.06797","created_at":"2026-07-05T03:44:50Z"},{"alias_kind":"arxiv_version","alias_value":"2010.06797v5","created_at":"2026-07-05T03:44:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.06797","created_at":"2026-07-05T03:44:50Z"},{"alias_kind":"pith_short_12","alias_value":"XKKMOSBACORT","created_at":"2026-07-05T03:44:50Z"},{"alias_kind":"pith_short_16","alias_value":"XKKMOSBACORT3AFM","created_at":"2026-07-05T03:44:50Z"},{"alias_kind":"pith_short_8","alias_value":"XKKMOSBA","created_at":"2026-07-05T03:44:50Z"}],"graph_snapshots":[{"event_id":"sha256:a43ff712a1e1d1018bc7d913324587b74020f40eb58d6dc9c4137bbd531efa02","target":"graph","created_at":"2026-07-05T03:44:50Z","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/2010.06797/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents a model-free reinforcement learning (RL) algorithm to synthesize a control policy that maximizes the satisfaction probability of linear temporal logic (LTL) specifications. Due to the consideration of environment and motion uncertainties, we model the robot motion as a probabilistic labeled Markov decision process with unknown transition probabilities and unknown probabilistic label functions. The LTL task specification is converted to a limit deterministic generalized B\\\"uchi automaton (LDGBA) with several accepting sets to maintain dense rewards during learning. The novel","authors_text":"Baoluo Li, Mingyu Cai, Shaoping Xiao, Zhen Kan, Zhiliang Li","cross_cats":["cs.AI","cs.RO","math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.FL","submitted_at":"2020-10-14T03:49:16Z","title":"Reinforcement Learning Based Temporal Logic Control with Maximum Probabilistic Satisfaction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.06797","kind":"arxiv","version":5},"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":"sha256:7ec41edeea13f6e7a02907ae71b4d05d520b125bb85e5caa1be4bf33b945720a","target":"record","created_at":"2026-07-05T03:44:50Z","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":"5f899a86e6f5731816258759b63f21b00caeaaa16aa43366f255642b078e84be","cross_cats_sorted":["cs.AI","cs.RO","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.FL","submitted_at":"2020-10-14T03:49:16Z","title_canon_sha256":"2b2d25bd8c4990c0f1f8d98774070468bc2cdf5f5496823efafa5e3f09075289"},"schema_version":"1.0","source":{"id":"2010.06797","kind":"arxiv","version":5}},"canonical_sha256":"ba94c7482013a33d80ac1ab3d2305cd22510148b54e418a9b581594cc30fa66d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ba94c7482013a33d80ac1ab3d2305cd22510148b54e418a9b581594cc30fa66d","first_computed_at":"2026-07-05T03:44:50.576067Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:44:50.576067Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DxhPSzKFhldsku5rX+/crm6VZXcbFu1Y6JB44UlWhrVZvCw8TIDfyO1VQBm70rR0c02kkndaD2FSxv2afJI7BA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:44:50.576509Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.06797","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7ec41edeea13f6e7a02907ae71b4d05d520b125bb85e5caa1be4bf33b945720a","sha256:a43ff712a1e1d1018bc7d913324587b74020f40eb58d6dc9c4137bbd531efa02"],"state_sha256":"65a47b74f01c026be52e1868f886a90262b712a041a79acf72d3bacb526c75fe"}