{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:7BBSEAB2IKTZLS5N7XJBNRXYD4","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":"7ffa3f5b7ad4486979c61cd29e1d34650f00b57954b6079413bef32e7142379c","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2023-11-28T18:59:58Z","title_canon_sha256":"05f710099d14a362fff42667478682dddb4455bd58fa2e4decc4775b257fb27b"},"schema_version":"1.0","source":{"id":"2311.17059","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.17059","created_at":"2026-07-05T10:52:09Z"},{"alias_kind":"arxiv_version","alias_value":"2311.17059v2","created_at":"2026-07-05T10:52:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.17059","created_at":"2026-07-05T10:52:09Z"},{"alias_kind":"pith_short_12","alias_value":"7BBSEAB2IKTZ","created_at":"2026-07-05T10:52:09Z"},{"alias_kind":"pith_short_16","alias_value":"7BBSEAB2IKTZLS5N","created_at":"2026-07-05T10:52:09Z"},{"alias_kind":"pith_short_8","alias_value":"7BBSEAB2","created_at":"2026-07-05T10:52:09Z"}],"graph_snapshots":[{"event_id":"sha256:127753a3fa25e1d7b29ccb3eca6baa8f4ad1eb89afc3e6f0b539ebc0bd1471f4","target":"graph","created_at":"2026-07-05T10:52:09Z","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/2311.17059/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper addresses the problem of designing control policies for agents with unknown stochastic dynamics and control objectives specified using Linear Temporal Logic (LTL). Recent Deep Reinforcement Learning (DRL) algorithms have aimed to compute policies that maximize the satisfaction probability of LTL formulas, but they often suffer from slow learning performance. To address this, we introduce a novel Deep Q-learning algorithm that significantly improves learning speed. The enhanced sample efficiency stems from a mission-driven exploration strategy that prioritizes exploration towards dir","authors_text":"Hosein Hasanbeig, Jun Wang, Kaiyuan Tan, Yiannis Kantaros, Zihe Sun","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2023-11-28T18:59:58Z","title":"Mission-driven Exploration for Accelerated Deep Reinforcement Learning with Temporal Logic Task Specifications"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.17059","kind":"arxiv","version":2},"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:a53d70ce2ebc65d9026d54143255fe6e90a8d2591f3c69971347bed6fd1f5d46","target":"record","created_at":"2026-07-05T10:52:09Z","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":"7ffa3f5b7ad4486979c61cd29e1d34650f00b57954b6079413bef32e7142379c","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2023-11-28T18:59:58Z","title_canon_sha256":"05f710099d14a362fff42667478682dddb4455bd58fa2e4decc4775b257fb27b"},"schema_version":"1.0","source":{"id":"2311.17059","kind":"arxiv","version":2}},"canonical_sha256":"f84322003a42a795cbadfdd216c6f81f3d5cc0750e0f2102a218ec8d939c76a0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f84322003a42a795cbadfdd216c6f81f3d5cc0750e0f2102a218ec8d939c76a0","first_computed_at":"2026-07-05T10:52:09.844808Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:52:09.844808Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bsurmuchgao8pVICSl9PxeD151UsAL52/KhY6Hod+b+RceFpjPpntJySfUOmTurWHC8ieymFvI1rLTg4rrHjBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:52:09.845345Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.17059","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a53d70ce2ebc65d9026d54143255fe6e90a8d2591f3c69971347bed6fd1f5d46","sha256:127753a3fa25e1d7b29ccb3eca6baa8f4ad1eb89afc3e6f0b539ebc0bd1471f4"],"state_sha256":"1f0a490d83f8b004ffd1cd66f18ce7147b595cfe4a621cc3553453ae65f55c35"}