{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:VQRTTT72HHQRQC4KPQOXFDPP4S","short_pith_number":"pith:VQRTTT72","schema_version":"1.0","canonical_sha256":"ac2339cffa39e1180b8a7c1d728defe48cd9950c77d24ca95a2f11d9f5725f03","source":{"kind":"arxiv","id":"1803.00444","version":3},"attestation_state":"computed","paper":{"title":"Inverse Reinforcement Learning via Nonparametric Spatio-Temporal Subgoal Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO","cs.SY","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abdelhak M. Zoubir, Adrian \\v{S}o\\v{s}i\\'c, Elmar Rueckert, Heinz Koeppl, Jan Peters","submitted_at":"2018-03-01T15:31:28Z","abstract_excerpt":"Advances in the field of inverse reinforcement learning (IRL) have led to sophisticated inference frameworks that relax the original modeling assumption of observing an agent behavior that reflects only a single intention. Instead of learning a global behavioral model, recent IRL methods divide the demonstration data into parts, to account for the fact that different trajectories may correspond to different intentions, e.g., because they were generated by different domain experts. In this work, we go one step further: using the intuitive concept of subgoals, we build upon the premise that even"},"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":"1803.00444","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-01T15:31:28Z","cross_cats_sorted":["cs.AI","cs.RO","cs.SY","stat.ML"],"title_canon_sha256":"fbd1bdc772d7d5aa1265b4c0b97366ee9fa00254f828eb463faa4b893459c7de","abstract_canon_sha256":"1ecf778644a4ca91b1671027a11be6780d0bce29e8681fa29e46b66589f55c94"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:32.970205Z","signature_b64":"6K59HJpR3HbG6zcL0DxoeOivB7+haws5zOkd8SP38wi6fJzWx20lyHUwkSlrsm5faN4j+b4QOCTHP9SS8XCLCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac2339cffa39e1180b8a7c1d728defe48cd9950c77d24ca95a2f11d9f5725f03","last_reissued_at":"2026-05-17T23:59:32.969607Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:32.969607Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Inverse Reinforcement Learning via Nonparametric Spatio-Temporal Subgoal Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO","cs.SY","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abdelhak M. Zoubir, Adrian \\v{S}o\\v{s}i\\'c, Elmar Rueckert, Heinz Koeppl, Jan Peters","submitted_at":"2018-03-01T15:31:28Z","abstract_excerpt":"Advances in the field of inverse reinforcement learning (IRL) have led to sophisticated inference frameworks that relax the original modeling assumption of observing an agent behavior that reflects only a single intention. Instead of learning a global behavioral model, recent IRL methods divide the demonstration data into parts, to account for the fact that different trajectories may correspond to different intentions, e.g., because they were generated by different domain experts. In this work, we go one step further: using the intuitive concept of subgoals, we build upon the premise that even"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.00444","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":""},"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":"1803.00444","created_at":"2026-05-17T23:59:32.969729+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.00444v3","created_at":"2026-05-17T23:59:32.969729+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.00444","created_at":"2026-05-17T23:59:32.969729+00:00"},{"alias_kind":"pith_short_12","alias_value":"VQRTTT72HHQR","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_16","alias_value":"VQRTTT72HHQRQC4K","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_8","alias_value":"VQRTTT72","created_at":"2026-05-18T12:32:59.047623+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/VQRTTT72HHQRQC4KPQOXFDPP4S","json":"https://pith.science/pith/VQRTTT72HHQRQC4KPQOXFDPP4S.json","graph_json":"https://pith.science/api/pith-number/VQRTTT72HHQRQC4KPQOXFDPP4S/graph.json","events_json":"https://pith.science/api/pith-number/VQRTTT72HHQRQC4KPQOXFDPP4S/events.json","paper":"https://pith.science/paper/VQRTTT72"},"agent_actions":{"view_html":"https://pith.science/pith/VQRTTT72HHQRQC4KPQOXFDPP4S","download_json":"https://pith.science/pith/VQRTTT72HHQRQC4KPQOXFDPP4S.json","view_paper":"https://pith.science/paper/VQRTTT72","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.00444&json=true","fetch_graph":"https://pith.science/api/pith-number/VQRTTT72HHQRQC4KPQOXFDPP4S/graph.json","fetch_events":"https://pith.science/api/pith-number/VQRTTT72HHQRQC4KPQOXFDPP4S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VQRTTT72HHQRQC4KPQOXFDPP4S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VQRTTT72HHQRQC4KPQOXFDPP4S/action/storage_attestation","attest_author":"https://pith.science/pith/VQRTTT72HHQRQC4KPQOXFDPP4S/action/author_attestation","sign_citation":"https://pith.science/pith/VQRTTT72HHQRQC4KPQOXFDPP4S/action/citation_signature","submit_replication":"https://pith.science/pith/VQRTTT72HHQRQC4KPQOXFDPP4S/action/replication_record"}},"created_at":"2026-05-17T23:59:32.969729+00:00","updated_at":"2026-05-17T23:59:32.969729+00:00"}