{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:CUNIWORW4LN7WL3G3GLNRTRQTZ","short_pith_number":"pith:CUNIWORW","schema_version":"1.0","canonical_sha256":"151a8b3a36e2dbfb2f66d996d8ce309e5ef529b91309e02be07e77b87c236dd4","source":{"kind":"arxiv","id":"2206.04477","version":2},"attestation_state":"computed","paper":{"title":"Receding Horizon Inverse Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"David Hsu, Wei Gao, Yiqing Xu","submitted_at":"2022-06-09T13:03:27Z","abstract_excerpt":"Inverse reinforcement learning (IRL) seeks to infer a cost function that explains the underlying goals and preferences of expert demonstrations. This paper presents receding horizon inverse reinforcement learning (RHIRL), a new IRL algorithm for high-dimensional, noisy, continuous systems with black-box dynamic models. RHIRL addresses two key challenges of IRL: scalability and robustness. To handle high-dimensional continuous systems, RHIRL matches the induced optimal trajectories with expert demonstrations locally in a receding horizon manner and 'stitches' together the local solutions to lea"},"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":"2206.04477","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-09T13:03:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fe5a773a823ed9e6f5f870b68d04bcc16e51b601c8c457da922de9f8c660ea81","abstract_canon_sha256":"3b388f88aaea4f6f5ecdec3d5816dd777882d5cf8289f5d46e453f109e217f37"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:07:00.077973Z","signature_b64":"dtqx9xSObMxL5R5n3VOBMFZQ/6y6QSN2Ed2+MY+EoibG+AQaAx3nvFlKbwfXmPIqe5YGYCOP0ejOXb1meoR3CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"151a8b3a36e2dbfb2f66d996d8ce309e5ef529b91309e02be07e77b87c236dd4","last_reissued_at":"2026-07-05T05:07:00.077476Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:07:00.077476Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Receding Horizon Inverse Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"David Hsu, Wei Gao, Yiqing Xu","submitted_at":"2022-06-09T13:03:27Z","abstract_excerpt":"Inverse reinforcement learning (IRL) seeks to infer a cost function that explains the underlying goals and preferences of expert demonstrations. This paper presents receding horizon inverse reinforcement learning (RHIRL), a new IRL algorithm for high-dimensional, noisy, continuous systems with black-box dynamic models. RHIRL addresses two key challenges of IRL: scalability and robustness. To handle high-dimensional continuous systems, RHIRL matches the induced optimal trajectories with expert demonstrations locally in a receding horizon manner and 'stitches' together the local solutions to lea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.04477","kind":"arxiv","version":2},"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/2206.04477/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":"2206.04477","created_at":"2026-07-05T05:07:00.077534+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.04477v2","created_at":"2026-07-05T05:07:00.077534+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.04477","created_at":"2026-07-05T05:07:00.077534+00:00"},{"alias_kind":"pith_short_12","alias_value":"CUNIWORW4LN7","created_at":"2026-07-05T05:07:00.077534+00:00"},{"alias_kind":"pith_short_16","alias_value":"CUNIWORW4LN7WL3G","created_at":"2026-07-05T05:07:00.077534+00:00"},{"alias_kind":"pith_short_8","alias_value":"CUNIWORW","created_at":"2026-07-05T05:07:00.077534+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/CUNIWORW4LN7WL3G3GLNRTRQTZ","json":"https://pith.science/pith/CUNIWORW4LN7WL3G3GLNRTRQTZ.json","graph_json":"https://pith.science/api/pith-number/CUNIWORW4LN7WL3G3GLNRTRQTZ/graph.json","events_json":"https://pith.science/api/pith-number/CUNIWORW4LN7WL3G3GLNRTRQTZ/events.json","paper":"https://pith.science/paper/CUNIWORW"},"agent_actions":{"view_html":"https://pith.science/pith/CUNIWORW4LN7WL3G3GLNRTRQTZ","download_json":"https://pith.science/pith/CUNIWORW4LN7WL3G3GLNRTRQTZ.json","view_paper":"https://pith.science/paper/CUNIWORW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.04477&json=true","fetch_graph":"https://pith.science/api/pith-number/CUNIWORW4LN7WL3G3GLNRTRQTZ/graph.json","fetch_events":"https://pith.science/api/pith-number/CUNIWORW4LN7WL3G3GLNRTRQTZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CUNIWORW4LN7WL3G3GLNRTRQTZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CUNIWORW4LN7WL3G3GLNRTRQTZ/action/storage_attestation","attest_author":"https://pith.science/pith/CUNIWORW4LN7WL3G3GLNRTRQTZ/action/author_attestation","sign_citation":"https://pith.science/pith/CUNIWORW4LN7WL3G3GLNRTRQTZ/action/citation_signature","submit_replication":"https://pith.science/pith/CUNIWORW4LN7WL3G3GLNRTRQTZ/action/replication_record"}},"created_at":"2026-07-05T05:07:00.077534+00:00","updated_at":"2026-07-05T05:07:00.077534+00:00"}