{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:CUNIWORW4LN7WL3G3GLNRTRQTZ","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":"3b388f88aaea4f6f5ecdec3d5816dd777882d5cf8289f5d46e453f109e217f37","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-09T13:03:27Z","title_canon_sha256":"fe5a773a823ed9e6f5f870b68d04bcc16e51b601c8c457da922de9f8c660ea81"},"schema_version":"1.0","source":{"id":"2206.04477","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.04477","created_at":"2026-07-05T05:07:00Z"},{"alias_kind":"arxiv_version","alias_value":"2206.04477v2","created_at":"2026-07-05T05:07:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.04477","created_at":"2026-07-05T05:07:00Z"},{"alias_kind":"pith_short_12","alias_value":"CUNIWORW4LN7","created_at":"2026-07-05T05:07:00Z"},{"alias_kind":"pith_short_16","alias_value":"CUNIWORW4LN7WL3G","created_at":"2026-07-05T05:07:00Z"},{"alias_kind":"pith_short_8","alias_value":"CUNIWORW","created_at":"2026-07-05T05:07:00Z"}],"graph_snapshots":[{"event_id":"sha256:c96d5c765e2a1fdc2120e2c0bbac05df8e1fc53d496e82b10b6dc328525706f8","target":"graph","created_at":"2026-07-05T05:07:00Z","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/2206.04477/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"David Hsu, Wei Gao, Yiqing Xu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-09T13:03:27Z","title":"Receding Horizon Inverse Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.04477","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":"sha256:43b5e1ac9a71c5b673cc6b0eff101a14833d427056319f0c65a679cc8826d9ec","target":"record","created_at":"2026-07-05T05:07:00Z","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":"3b388f88aaea4f6f5ecdec3d5816dd777882d5cf8289f5d46e453f109e217f37","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-09T13:03:27Z","title_canon_sha256":"fe5a773a823ed9e6f5f870b68d04bcc16e51b601c8c457da922de9f8c660ea81"},"schema_version":"1.0","source":{"id":"2206.04477","kind":"arxiv","version":2}},"canonical_sha256":"151a8b3a36e2dbfb2f66d996d8ce309e5ef529b91309e02be07e77b87c236dd4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"151a8b3a36e2dbfb2f66d996d8ce309e5ef529b91309e02be07e77b87c236dd4","first_computed_at":"2026-07-05T05:07:00.077476Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:07:00.077476Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dtqx9xSObMxL5R5n3VOBMFZQ/6y6QSN2Ed2+MY+EoibG+AQaAx3nvFlKbwfXmPIqe5YGYCOP0ejOXb1meoR3CA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:07:00.077973Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.04477","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:43b5e1ac9a71c5b673cc6b0eff101a14833d427056319f0c65a679cc8826d9ec","sha256:c96d5c765e2a1fdc2120e2c0bbac05df8e1fc53d496e82b10b6dc328525706f8"],"state_sha256":"26eae86a106b9244a0eb4380d41f586d0760431d578808d4fb4b1bdcff91c47c"}