{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:OBVPL2HO6DB2XTDJPMKU2O6GCY","short_pith_number":"pith:OBVPL2HO","schema_version":"1.0","canonical_sha256":"706af5e8eef0c3abcc697b154d3bc61614d30702c8a91faa6b844d32bd8d3346","source":{"kind":"arxiv","id":"1802.06604","version":3},"attestation_state":"computed","paper":{"title":"Learning High-level Representations from Demonstrations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Garrett Andersen, Haitham Bou-Ammar, Peter Vrancx","submitted_at":"2018-02-19T12:11:16Z","abstract_excerpt":"Hierarchical learning (HL) is key to solving complex sequential decision problems with long horizons and sparse rewards. It allows learning agents to break-up large problems into smaller, more manageable subtasks. A common approach to HL, is to provide the agent with a number of high-level skills that solve small parts of the overall problem. A major open question, however, is how to identify a suitable set of reusable skills. We propose a principled approach that uses human demonstrations to infer a set of subgoals based on changes in the demonstration dynamics. Using these subgoals, we decom"},"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":"1802.06604","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-02-19T12:11:16Z","cross_cats_sorted":[],"title_canon_sha256":"95a0c94bd685954db02b5047e298a5e84c6958aad433ce381b0fe95881f7b50f","abstract_canon_sha256":"636b41eff7432db35c3fc0f9e77931707fe4de524142201322b7f1235ffedf79"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:18.285024Z","signature_b64":"sieT/Uiy17Im4IrmQ023DrN6ZeLw1murM3QoH0yVT7ddnaXAbOtPy+XmOv05dnEdU+TTTqw5yBS5sEZRsmZJCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"706af5e8eef0c3abcc697b154d3bc61614d30702c8a91faa6b844d32bd8d3346","last_reissued_at":"2026-05-18T00:22:18.284566Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:18.284566Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning High-level Representations from Demonstrations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Garrett Andersen, Haitham Bou-Ammar, Peter Vrancx","submitted_at":"2018-02-19T12:11:16Z","abstract_excerpt":"Hierarchical learning (HL) is key to solving complex sequential decision problems with long horizons and sparse rewards. It allows learning agents to break-up large problems into smaller, more manageable subtasks. A common approach to HL, is to provide the agent with a number of high-level skills that solve small parts of the overall problem. A major open question, however, is how to identify a suitable set of reusable skills. We propose a principled approach that uses human demonstrations to infer a set of subgoals based on changes in the demonstration dynamics. Using these subgoals, we decom"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.06604","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":"1802.06604","created_at":"2026-05-18T00:22:18.284637+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.06604v3","created_at":"2026-05-18T00:22:18.284637+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.06604","created_at":"2026-05-18T00:22:18.284637+00:00"},{"alias_kind":"pith_short_12","alias_value":"OBVPL2HO6DB2","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_16","alias_value":"OBVPL2HO6DB2XTDJ","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_8","alias_value":"OBVPL2HO","created_at":"2026-05-18T12:32:43.782077+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/OBVPL2HO6DB2XTDJPMKU2O6GCY","json":"https://pith.science/pith/OBVPL2HO6DB2XTDJPMKU2O6GCY.json","graph_json":"https://pith.science/api/pith-number/OBVPL2HO6DB2XTDJPMKU2O6GCY/graph.json","events_json":"https://pith.science/api/pith-number/OBVPL2HO6DB2XTDJPMKU2O6GCY/events.json","paper":"https://pith.science/paper/OBVPL2HO"},"agent_actions":{"view_html":"https://pith.science/pith/OBVPL2HO6DB2XTDJPMKU2O6GCY","download_json":"https://pith.science/pith/OBVPL2HO6DB2XTDJPMKU2O6GCY.json","view_paper":"https://pith.science/paper/OBVPL2HO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.06604&json=true","fetch_graph":"https://pith.science/api/pith-number/OBVPL2HO6DB2XTDJPMKU2O6GCY/graph.json","fetch_events":"https://pith.science/api/pith-number/OBVPL2HO6DB2XTDJPMKU2O6GCY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OBVPL2HO6DB2XTDJPMKU2O6GCY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OBVPL2HO6DB2XTDJPMKU2O6GCY/action/storage_attestation","attest_author":"https://pith.science/pith/OBVPL2HO6DB2XTDJPMKU2O6GCY/action/author_attestation","sign_citation":"https://pith.science/pith/OBVPL2HO6DB2XTDJPMKU2O6GCY/action/citation_signature","submit_replication":"https://pith.science/pith/OBVPL2HO6DB2XTDJPMKU2O6GCY/action/replication_record"}},"created_at":"2026-05-18T00:22:18.284637+00:00","updated_at":"2026-05-18T00:22:18.284637+00:00"}