{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:3Z3GZJAPPJHNU3EFA3MN5AFEWV","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":"5b46bcad2fabd122c2b892ed8baddebcf90342e037eea5f166da3777af2ae6ad","cross_cats_sorted":["cs.AI","cs.LO","cs.SY","eess.SY","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-23T18:10:00Z","title_canon_sha256":"1dd7195475b7ded53764122ad4f14270cb208a76d437c513c36c75c5a537a36c"},"schema_version":"1.0","source":{"id":"1909.11591","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.11591","created_at":"2026-07-05T00:21:37Z"},{"alias_kind":"arxiv_version","alias_value":"1909.11591v2","created_at":"2026-07-05T00:21:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.11591","created_at":"2026-07-05T00:21:37Z"},{"alias_kind":"pith_short_12","alias_value":"3Z3GZJAPPJHN","created_at":"2026-07-05T00:21:37Z"},{"alias_kind":"pith_short_16","alias_value":"3Z3GZJAPPJHNU3EF","created_at":"2026-07-05T00:21:37Z"},{"alias_kind":"pith_short_8","alias_value":"3Z3GZJAP","created_at":"2026-07-05T00:21:37Z"}],"graph_snapshots":[{"event_id":"sha256:619b24d64dea4c6f1f9fb2045cf6d44341d8fe10eef6bace022453e03bb453cd","target":"graph","created_at":"2026-07-05T00:21:37Z","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/1909.11591/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose an actor-critic, model-free, and online Reinforcement Learning (RL) framework for continuous-state continuous-action Markov Decision Processes (MDPs) when the reward is highly sparse but encompasses a high-level temporal structure. We represent this temporal structure by a finite-state machine and construct an on-the-fly synchronised product with the MDP and the finite machine. The temporal structure acts as a guide for the RL agent within the product, where a modular Deep Deterministic Policy Gradient (DDPG) architecture is proposed to generate a low-level control policy. We evalua","authors_text":"Alessandro Abate, Daniel Kroening, Lim Zun Yuan, Mohammadhosein Hasanbeig","cross_cats":["cs.AI","cs.LO","cs.SY","eess.SY","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-23T18:10:00Z","title":"Modular Deep Reinforcement Learning with Temporal Logic Specifications"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.11591","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:ebafad5ad3dfe1a0268f8d4b09516fb9a72dec568bbdd39c7632ad6cad71a4a8","target":"record","created_at":"2026-07-05T00:21:37Z","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":"5b46bcad2fabd122c2b892ed8baddebcf90342e037eea5f166da3777af2ae6ad","cross_cats_sorted":["cs.AI","cs.LO","cs.SY","eess.SY","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-23T18:10:00Z","title_canon_sha256":"1dd7195475b7ded53764122ad4f14270cb208a76d437c513c36c75c5a537a36c"},"schema_version":"1.0","source":{"id":"1909.11591","kind":"arxiv","version":2}},"canonical_sha256":"de766ca40f7a4eda6c8506d8de80a4b5641b4245548df9cdf1d27f6a366d69c6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"de766ca40f7a4eda6c8506d8de80a4b5641b4245548df9cdf1d27f6a366d69c6","first_computed_at":"2026-07-05T00:21:37.177933Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:21:37.177933Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AoBox9LQd6kLvZHOc+WawqHls5ljE7VLNzeLYh7pZLiL+doltcR7FIEcvpRSAMdjgdzuUPj7P9vXNEuB4ZOSBg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:21:37.178491Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.11591","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ebafad5ad3dfe1a0268f8d4b09516fb9a72dec568bbdd39c7632ad6cad71a4a8","sha256:619b24d64dea4c6f1f9fb2045cf6d44341d8fe10eef6bace022453e03bb453cd"],"state_sha256":"d0234ada43a0a40a010a486da3d0fad038e3c38a3ae5e8f9edc78e4f5388d4a4"}