{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:BJWN3PGBDP2FV5NIC7LFYMU73Z","short_pith_number":"pith:BJWN3PGB","schema_version":"1.0","canonical_sha256":"0a6cddbcc11bf45af5a817d65c329fde590c46ec6eb2a6ab28a456ea632ca253","source":{"kind":"arxiv","id":"1806.08479","version":1},"attestation_state":"computed","paper":{"title":"Human-Interactive Subgoal Supervision for Efficient Inverse Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.HC","authors_text":"Eshed Ohn-Bar, Kris M. Kitani, Nicholas Rhinehart, Xinlei Pan, Yan Xu, Yilin Shen","submitted_at":"2018-06-22T03:24:00Z","abstract_excerpt":"Humans are able to understand and perform complex tasks by strategically structuring the tasks into incremental steps or subgoals. For a robot attempting to learn to perform a sequential task with critical subgoal states, such states can provide a natural opportunity for interaction with a human expert. This paper analyzes the benefit of incorporating a notion of subgoals into Inverse Reinforcement Learning (IRL) with a Human-In-The-Loop (HITL) framework. The learning process is interactive, with a human expert first providing input in the form of full demonstrations along with some subgoal st"},"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":"1806.08479","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2018-06-22T03:24:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"601d299fcd43b85e5a49ad983a033c794a49a520105922027e607b782f8f1b0f","abstract_canon_sha256":"3d0c23dd8a7207ebfeb9c677e8887731536d467dbb12855bca97bcd3be94a1ac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:12:37.138469Z","signature_b64":"EFnPRQhU87zJm9EHIuIxWxoGQSG33D60OkHblTdG38qP3rSxBKcKxGXZMblX5VB9O4g3tfO9LqRRA/TOzltFAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a6cddbcc11bf45af5a817d65c329fde590c46ec6eb2a6ab28a456ea632ca253","last_reissued_at":"2026-05-18T00:12:37.137872Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:12:37.137872Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Human-Interactive Subgoal Supervision for Efficient Inverse Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.HC","authors_text":"Eshed Ohn-Bar, Kris M. Kitani, Nicholas Rhinehart, Xinlei Pan, Yan Xu, Yilin Shen","submitted_at":"2018-06-22T03:24:00Z","abstract_excerpt":"Humans are able to understand and perform complex tasks by strategically structuring the tasks into incremental steps or subgoals. For a robot attempting to learn to perform a sequential task with critical subgoal states, such states can provide a natural opportunity for interaction with a human expert. This paper analyzes the benefit of incorporating a notion of subgoals into Inverse Reinforcement Learning (IRL) with a Human-In-The-Loop (HITL) framework. The learning process is interactive, with a human expert first providing input in the form of full demonstrations along with some subgoal st"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.08479","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":"1806.08479","created_at":"2026-05-18T00:12:37.137957+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.08479v1","created_at":"2026-05-18T00:12:37.137957+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.08479","created_at":"2026-05-18T00:12:37.137957+00:00"},{"alias_kind":"pith_short_12","alias_value":"BJWN3PGBDP2F","created_at":"2026-05-18T12:32:16.446611+00:00"},{"alias_kind":"pith_short_16","alias_value":"BJWN3PGBDP2FV5NI","created_at":"2026-05-18T12:32:16.446611+00:00"},{"alias_kind":"pith_short_8","alias_value":"BJWN3PGB","created_at":"2026-05-18T12:32:16.446611+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/BJWN3PGBDP2FV5NIC7LFYMU73Z","json":"https://pith.science/pith/BJWN3PGBDP2FV5NIC7LFYMU73Z.json","graph_json":"https://pith.science/api/pith-number/BJWN3PGBDP2FV5NIC7LFYMU73Z/graph.json","events_json":"https://pith.science/api/pith-number/BJWN3PGBDP2FV5NIC7LFYMU73Z/events.json","paper":"https://pith.science/paper/BJWN3PGB"},"agent_actions":{"view_html":"https://pith.science/pith/BJWN3PGBDP2FV5NIC7LFYMU73Z","download_json":"https://pith.science/pith/BJWN3PGBDP2FV5NIC7LFYMU73Z.json","view_paper":"https://pith.science/paper/BJWN3PGB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.08479&json=true","fetch_graph":"https://pith.science/api/pith-number/BJWN3PGBDP2FV5NIC7LFYMU73Z/graph.json","fetch_events":"https://pith.science/api/pith-number/BJWN3PGBDP2FV5NIC7LFYMU73Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BJWN3PGBDP2FV5NIC7LFYMU73Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BJWN3PGBDP2FV5NIC7LFYMU73Z/action/storage_attestation","attest_author":"https://pith.science/pith/BJWN3PGBDP2FV5NIC7LFYMU73Z/action/author_attestation","sign_citation":"https://pith.science/pith/BJWN3PGBDP2FV5NIC7LFYMU73Z/action/citation_signature","submit_replication":"https://pith.science/pith/BJWN3PGBDP2FV5NIC7LFYMU73Z/action/replication_record"}},"created_at":"2026-05-18T00:12:37.137957+00:00","updated_at":"2026-05-18T00:12:37.137957+00:00"}