{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:34AD66JLT47YOEMLO72GNO3W3B","short_pith_number":"pith:34AD66JL","schema_version":"1.0","canonical_sha256":"df003f792b9f3f87118b77f466bb76d85164afaf6ef68fc9cafcd0f817ea49e1","source":{"kind":"arxiv","id":"1604.06508","version":1},"attestation_state":"computed","paper":{"title":"HIRL: Hierarchical Inverse Reinforcement Learning for Long-Horizon Tasks with Delayed Rewards","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Animesh Garg, Florian T. Pokorny, Ken Goldberg, Lauren Miller, Richard Liaw, Sanjay Krishnan","submitted_at":"2016-04-21T22:14:11Z","abstract_excerpt":"Reinforcement Learning (RL) struggles in problems with delayed rewards, and one approach is to segment the task into sub-tasks with incremental rewards. We propose a framework called Hierarchical Inverse Reinforcement Learning (HIRL), which is a model for learning sub-task structure from demonstrations. HIRL decomposes the task into sub-tasks based on transitions that are consistent across demonstrations. These transitions are defined as changes in local linearity w.r.t to a kernel function. Then, HIRL uses the inferred structure to learn reward functions local to the sub-tasks but also handle"},"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":"1604.06508","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2016-04-21T22:14:11Z","cross_cats_sorted":[],"title_canon_sha256":"6e6b907d4b64a8d1ae2b3ae3d63f83861b32010c4a95988ff15484bbfa59bdd1","abstract_canon_sha256":"2925b8013bbcb9c17fd4337362df9550ad2131e87c796fc83680bef51c0fadba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:16:28.885293Z","signature_b64":"n+AafI7F66AFw1/u16Fdie4AGFPGxPpo5dSC3yFS9PTmYQ8ai7n7QrrHgT1UqfTVgGI4SdIUGFxqFBnu/EcYCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df003f792b9f3f87118b77f466bb76d85164afaf6ef68fc9cafcd0f817ea49e1","last_reissued_at":"2026-05-18T01:16:28.884834Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:16:28.884834Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HIRL: Hierarchical Inverse Reinforcement Learning for Long-Horizon Tasks with Delayed Rewards","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Animesh Garg, Florian T. Pokorny, Ken Goldberg, Lauren Miller, Richard Liaw, Sanjay Krishnan","submitted_at":"2016-04-21T22:14:11Z","abstract_excerpt":"Reinforcement Learning (RL) struggles in problems with delayed rewards, and one approach is to segment the task into sub-tasks with incremental rewards. We propose a framework called Hierarchical Inverse Reinforcement Learning (HIRL), which is a model for learning sub-task structure from demonstrations. HIRL decomposes the task into sub-tasks based on transitions that are consistent across demonstrations. These transitions are defined as changes in local linearity w.r.t to a kernel function. Then, HIRL uses the inferred structure to learn reward functions local to the sub-tasks but also handle"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1604.06508","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":""},"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":"1604.06508","created_at":"2026-05-18T01:16:28.884912+00:00"},{"alias_kind":"arxiv_version","alias_value":"1604.06508v1","created_at":"2026-05-18T01:16:28.884912+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1604.06508","created_at":"2026-05-18T01:16:28.884912+00:00"},{"alias_kind":"pith_short_12","alias_value":"34AD66JLT47Y","created_at":"2026-05-18T12:29:55.572404+00:00"},{"alias_kind":"pith_short_16","alias_value":"34AD66JLT47YOEML","created_at":"2026-05-18T12:29:55.572404+00:00"},{"alias_kind":"pith_short_8","alias_value":"34AD66JL","created_at":"2026-05-18T12:29:55.572404+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/34AD66JLT47YOEMLO72GNO3W3B","json":"https://pith.science/pith/34AD66JLT47YOEMLO72GNO3W3B.json","graph_json":"https://pith.science/api/pith-number/34AD66JLT47YOEMLO72GNO3W3B/graph.json","events_json":"https://pith.science/api/pith-number/34AD66JLT47YOEMLO72GNO3W3B/events.json","paper":"https://pith.science/paper/34AD66JL"},"agent_actions":{"view_html":"https://pith.science/pith/34AD66JLT47YOEMLO72GNO3W3B","download_json":"https://pith.science/pith/34AD66JLT47YOEMLO72GNO3W3B.json","view_paper":"https://pith.science/paper/34AD66JL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1604.06508&json=true","fetch_graph":"https://pith.science/api/pith-number/34AD66JLT47YOEMLO72GNO3W3B/graph.json","fetch_events":"https://pith.science/api/pith-number/34AD66JLT47YOEMLO72GNO3W3B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/34AD66JLT47YOEMLO72GNO3W3B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/34AD66JLT47YOEMLO72GNO3W3B/action/storage_attestation","attest_author":"https://pith.science/pith/34AD66JLT47YOEMLO72GNO3W3B/action/author_attestation","sign_citation":"https://pith.science/pith/34AD66JLT47YOEMLO72GNO3W3B/action/citation_signature","submit_replication":"https://pith.science/pith/34AD66JLT47YOEMLO72GNO3W3B/action/replication_record"}},"created_at":"2026-05-18T01:16:28.884912+00:00","updated_at":"2026-05-18T01:16:28.884912+00:00"}