{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:XKKMOSBACORT3AFMDKZ5EMC42I","short_pith_number":"pith:XKKMOSBA","schema_version":"1.0","canonical_sha256":"ba94c7482013a33d80ac1ab3d2305cd22510148b54e418a9b581594cc30fa66d","source":{"kind":"arxiv","id":"2010.06797","version":5},"attestation_state":"computed","paper":{"title":"Reinforcement Learning Based Temporal Logic Control with Maximum Probabilistic Satisfaction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO","math.OC"],"primary_cat":"cs.FL","authors_text":"Baoluo Li, Mingyu Cai, Shaoping Xiao, Zhen Kan, Zhiliang Li","submitted_at":"2020-10-14T03:49:16Z","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"},"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":"2010.06797","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.FL","submitted_at":"2020-10-14T03:49:16Z","cross_cats_sorted":["cs.AI","cs.RO","math.OC"],"title_canon_sha256":"2b2d25bd8c4990c0f1f8d98774070468bc2cdf5f5496823efafa5e3f09075289","abstract_canon_sha256":"5f899a86e6f5731816258759b63f21b00caeaaa16aa43366f255642b078e84be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:44:50.576509Z","signature_b64":"DxhPSzKFhldsku5rX+/crm6VZXcbFu1Y6JB44UlWhrVZvCw8TIDfyO1VQBm70rR0c02kkndaD2FSxv2afJI7BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba94c7482013a33d80ac1ab3d2305cd22510148b54e418a9b581594cc30fa66d","last_reissued_at":"2026-07-05T03:44:50.576067Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:44:50.576067Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning Based Temporal Logic Control with Maximum Probabilistic Satisfaction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO","math.OC"],"primary_cat":"cs.FL","authors_text":"Baoluo Li, Mingyu Cai, Shaoping Xiao, Zhen Kan, Zhiliang Li","submitted_at":"2020-10-14T03:49:16Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.06797","kind":"arxiv","version":5},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2010.06797/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2010.06797","created_at":"2026-07-05T03:44:50.576123+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.06797v5","created_at":"2026-07-05T03:44:50.576123+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.06797","created_at":"2026-07-05T03:44:50.576123+00:00"},{"alias_kind":"pith_short_12","alias_value":"XKKMOSBACORT","created_at":"2026-07-05T03:44:50.576123+00:00"},{"alias_kind":"pith_short_16","alias_value":"XKKMOSBACORT3AFM","created_at":"2026-07-05T03:44:50.576123+00:00"},{"alias_kind":"pith_short_8","alias_value":"XKKMOSBA","created_at":"2026-07-05T03:44:50.576123+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.12019","citing_title":"Regret-Free Reinforcement Learning for LTL Specifications","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XKKMOSBACORT3AFMDKZ5EMC42I","json":"https://pith.science/pith/XKKMOSBACORT3AFMDKZ5EMC42I.json","graph_json":"https://pith.science/api/pith-number/XKKMOSBACORT3AFMDKZ5EMC42I/graph.json","events_json":"https://pith.science/api/pith-number/XKKMOSBACORT3AFMDKZ5EMC42I/events.json","paper":"https://pith.science/paper/XKKMOSBA"},"agent_actions":{"view_html":"https://pith.science/pith/XKKMOSBACORT3AFMDKZ5EMC42I","download_json":"https://pith.science/pith/XKKMOSBACORT3AFMDKZ5EMC42I.json","view_paper":"https://pith.science/paper/XKKMOSBA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.06797&json=true","fetch_graph":"https://pith.science/api/pith-number/XKKMOSBACORT3AFMDKZ5EMC42I/graph.json","fetch_events":"https://pith.science/api/pith-number/XKKMOSBACORT3AFMDKZ5EMC42I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XKKMOSBACORT3AFMDKZ5EMC42I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XKKMOSBACORT3AFMDKZ5EMC42I/action/storage_attestation","attest_author":"https://pith.science/pith/XKKMOSBACORT3AFMDKZ5EMC42I/action/author_attestation","sign_citation":"https://pith.science/pith/XKKMOSBACORT3AFMDKZ5EMC42I/action/citation_signature","submit_replication":"https://pith.science/pith/XKKMOSBACORT3AFMDKZ5EMC42I/action/replication_record"}},"created_at":"2026-07-05T03:44:50.576123+00:00","updated_at":"2026-07-05T03:44:50.576123+00:00"}