{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:FFP47XV3VPAEDLFIRKKFFCXF52","short_pith_number":"pith:FFP47XV3","schema_version":"1.0","canonical_sha256":"295fcfdebbabc041aca88a94528ae5eeadfcd200a041b97231026e6176dd11ab","source":{"kind":"arxiv","id":"2104.04483","version":3},"attestation_state":"computed","paper":{"title":"Inverse Reinforcement Learning: A Control Lyapunov Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Armin Lederer, Samuel Tesfazgi, Sandra Hirche","submitted_at":"2021-04-09T17:08:16Z","abstract_excerpt":"Inferring the intent of an intelligent agent from demonstrations and subsequently predicting its behavior, is a critical task in many collaborative settings. A common approach to solve this problem is the framework of inverse reinforcement learning (IRL), where the observed agent, e.g., a human demonstrator, is assumed to behave according to an intrinsic cost function that reflects its intent and informs its control actions. In this work, we reformulate the IRL inference problem to learning control Lyapunov functions (CLF) from demonstrations by exploiting the inverse optimality property, whic"},"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":"2104.04483","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-09T17:08:16Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"6cf7c84faa3ed87dd644fd2e43ce66ee3d442a58b0f3a8d95bedbc93449edf14","abstract_canon_sha256":"df7c2a397b3f604d369a79aa0380eb2bf7029ab3292ca17789c666f6dbdb2854"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:19:43.017038Z","signature_b64":"/XYntrPE09Cl4jPZKENqd0fbl5x/syWaeRd2Ym1wjL607yXaT0M9rvkcz7XvJSojAmC/+zgfv08T88H03z3wBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"295fcfdebbabc041aca88a94528ae5eeadfcd200a041b97231026e6176dd11ab","last_reissued_at":"2026-07-05T03:19:43.016569Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:19:43.016569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Inverse Reinforcement Learning: A Control Lyapunov Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Armin Lederer, Samuel Tesfazgi, Sandra Hirche","submitted_at":"2021-04-09T17:08:16Z","abstract_excerpt":"Inferring the intent of an intelligent agent from demonstrations and subsequently predicting its behavior, is a critical task in many collaborative settings. A common approach to solve this problem is the framework of inverse reinforcement learning (IRL), where the observed agent, e.g., a human demonstrator, is assumed to behave according to an intrinsic cost function that reflects its intent and informs its control actions. In this work, we reformulate the IRL inference problem to learning control Lyapunov functions (CLF) from demonstrations by exploiting the inverse optimality property, whic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.04483","kind":"arxiv","version":3},"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/2104.04483/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":"2104.04483","created_at":"2026-07-05T03:19:43.016623+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.04483v3","created_at":"2026-07-05T03:19:43.016623+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.04483","created_at":"2026-07-05T03:19:43.016623+00:00"},{"alias_kind":"pith_short_12","alias_value":"FFP47XV3VPAE","created_at":"2026-07-05T03:19:43.016623+00:00"},{"alias_kind":"pith_short_16","alias_value":"FFP47XV3VPAEDLFI","created_at":"2026-07-05T03:19:43.016623+00:00"},{"alias_kind":"pith_short_8","alias_value":"FFP47XV3","created_at":"2026-07-05T03:19:43.016623+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FFP47XV3VPAEDLFIRKKFFCXF52","json":"https://pith.science/pith/FFP47XV3VPAEDLFIRKKFFCXF52.json","graph_json":"https://pith.science/api/pith-number/FFP47XV3VPAEDLFIRKKFFCXF52/graph.json","events_json":"https://pith.science/api/pith-number/FFP47XV3VPAEDLFIRKKFFCXF52/events.json","paper":"https://pith.science/paper/FFP47XV3"},"agent_actions":{"view_html":"https://pith.science/pith/FFP47XV3VPAEDLFIRKKFFCXF52","download_json":"https://pith.science/pith/FFP47XV3VPAEDLFIRKKFFCXF52.json","view_paper":"https://pith.science/paper/FFP47XV3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.04483&json=true","fetch_graph":"https://pith.science/api/pith-number/FFP47XV3VPAEDLFIRKKFFCXF52/graph.json","fetch_events":"https://pith.science/api/pith-number/FFP47XV3VPAEDLFIRKKFFCXF52/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FFP47XV3VPAEDLFIRKKFFCXF52/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FFP47XV3VPAEDLFIRKKFFCXF52/action/storage_attestation","attest_author":"https://pith.science/pith/FFP47XV3VPAEDLFIRKKFFCXF52/action/author_attestation","sign_citation":"https://pith.science/pith/FFP47XV3VPAEDLFIRKKFFCXF52/action/citation_signature","submit_replication":"https://pith.science/pith/FFP47XV3VPAEDLFIRKKFFCXF52/action/replication_record"}},"created_at":"2026-07-05T03:19:43.016623+00:00","updated_at":"2026-07-05T03:19:43.016623+00:00"}