{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:W6RYDFU5FDCTSFEHYDQWGVINPE","short_pith_number":"pith:W6RYDFU5","schema_version":"1.0","canonical_sha256":"b7a381969d28c5391487c0e163550d7935a8c07f4b4788f34368f05de7df3d0d","source":{"kind":"arxiv","id":"2011.04950","version":1},"attestation_state":"computed","paper":{"title":"Model-based Reinforcement Learning from Signal Temporal Logic Specifications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SY","eess.SY"],"primary_cat":"cs.RO","authors_text":"Anand Balakrishnan, Jyotirmoy V. Deshmukh, Parv Kapoor","submitted_at":"2020-11-10T07:31:47Z","abstract_excerpt":"Techniques based on Reinforcement Learning (RL) are increasingly being used to design control policies for robotic systems. RL fundamentally relies on state-based reward functions to encode desired behavior of the robot and bad reward functions are prone to exploitation by the learning agent, leading to behavior that is undesirable in the best case and critically dangerous in the worst. On the other hand, designing good reward functions for complex tasks is a challenging problem. In this paper, we propose expressing desired high-level robot behavior using a formal specification language known "},"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":"2011.04950","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2020-11-10T07:31:47Z","cross_cats_sorted":["cs.AI","cs.SY","eess.SY"],"title_canon_sha256":"3aceecda14a5fb517db366410053b1797804bf3423ab2e662fd296282bfd01d6","abstract_canon_sha256":"98a741f02c7cc33a0668554b15be28fe99b0b70c727e5150153f8ed64f4653d9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:50:41.942147Z","signature_b64":"cAolP+8TQHPmIKDvQzKBWLWShk9G/Q0h5j5gg2IQ/vNI4hTM2JBe6OpeMcpbexMXP+nWnbbsdL7m+5o0K3sECQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b7a381969d28c5391487c0e163550d7935a8c07f4b4788f34368f05de7df3d0d","last_reissued_at":"2026-07-05T01:50:41.941744Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:50:41.941744Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Model-based Reinforcement Learning from Signal Temporal Logic Specifications","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SY","eess.SY"],"primary_cat":"cs.RO","authors_text":"Anand Balakrishnan, Jyotirmoy V. Deshmukh, Parv Kapoor","submitted_at":"2020-11-10T07:31:47Z","abstract_excerpt":"Techniques based on Reinforcement Learning (RL) are increasingly being used to design control policies for robotic systems. RL fundamentally relies on state-based reward functions to encode desired behavior of the robot and bad reward functions are prone to exploitation by the learning agent, leading to behavior that is undesirable in the best case and critically dangerous in the worst. On the other hand, designing good reward functions for complex tasks is a challenging problem. In this paper, we propose expressing desired high-level robot behavior using a formal specification language known "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.04950","kind":"arxiv","version":1},"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/2011.04950/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":"2011.04950","created_at":"2026-07-05T01:50:41.941800+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.04950v1","created_at":"2026-07-05T01:50:41.941800+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.04950","created_at":"2026-07-05T01:50:41.941800+00:00"},{"alias_kind":"pith_short_12","alias_value":"W6RYDFU5FDCT","created_at":"2026-07-05T01:50:41.941800+00:00"},{"alias_kind":"pith_short_16","alias_value":"W6RYDFU5FDCTSFEH","created_at":"2026-07-05T01:50:41.941800+00:00"},{"alias_kind":"pith_short_8","alias_value":"W6RYDFU5","created_at":"2026-07-05T01:50:41.941800+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00442","citing_title":"Learning Gait-Aware Quadruped Locomotion with Temporal Logic Specifications","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18343","citing_title":"DAG-STL: A Hierarchical Framework for Zero-Shot Trajectory Planning under Signal Temporal Logic Specifications","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14440","citing_title":"On Tackling Complex Tasks with Reward Machines and Signal Temporal Logics","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W6RYDFU5FDCTSFEHYDQWGVINPE","json":"https://pith.science/pith/W6RYDFU5FDCTSFEHYDQWGVINPE.json","graph_json":"https://pith.science/api/pith-number/W6RYDFU5FDCTSFEHYDQWGVINPE/graph.json","events_json":"https://pith.science/api/pith-number/W6RYDFU5FDCTSFEHYDQWGVINPE/events.json","paper":"https://pith.science/paper/W6RYDFU5"},"agent_actions":{"view_html":"https://pith.science/pith/W6RYDFU5FDCTSFEHYDQWGVINPE","download_json":"https://pith.science/pith/W6RYDFU5FDCTSFEHYDQWGVINPE.json","view_paper":"https://pith.science/paper/W6RYDFU5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.04950&json=true","fetch_graph":"https://pith.science/api/pith-number/W6RYDFU5FDCTSFEHYDQWGVINPE/graph.json","fetch_events":"https://pith.science/api/pith-number/W6RYDFU5FDCTSFEHYDQWGVINPE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W6RYDFU5FDCTSFEHYDQWGVINPE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W6RYDFU5FDCTSFEHYDQWGVINPE/action/storage_attestation","attest_author":"https://pith.science/pith/W6RYDFU5FDCTSFEHYDQWGVINPE/action/author_attestation","sign_citation":"https://pith.science/pith/W6RYDFU5FDCTSFEHYDQWGVINPE/action/citation_signature","submit_replication":"https://pith.science/pith/W6RYDFU5FDCTSFEHYDQWGVINPE/action/replication_record"}},"created_at":"2026-07-05T01:50:41.941800+00:00","updated_at":"2026-07-05T01:50:41.941800+00:00"}