{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:DNJW3O4P2VTDCCQO7IX4DIKZ35","short_pith_number":"pith:DNJW3O4P","schema_version":"1.0","canonical_sha256":"1b536dbb8fd566310a0efa2fc1a159df7755b7ec510e50dd9712096c5ba60724","source":{"kind":"arxiv","id":"1708.00463","version":1},"attestation_state":"computed","paper":{"title":"Hierarchical Subtask Discovery With Non-Negative Matrix Factorization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Adam C. Earle, Andrew M. Saxe, Benjamin Rosman","submitted_at":"2017-08-01T18:19:40Z","abstract_excerpt":"Hierarchical reinforcement learning methods offer a powerful means of planning flexible behavior in complicated domains. However, learning an appropriate hierarchical decomposition of a domain into subtasks remains a substantial challenge. We present a novel algorithm for subtask discovery, based on the recently introduced multitask linearly-solvable Markov decision process (MLMDP) framework. The MLMDP can perform never-before-seen tasks by representing them as a linear combination of a previously learned basis set of tasks. In this setting, the subtask discovery problem can naturally be posed"},"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":"1708.00463","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-08-01T18:19:40Z","cross_cats_sorted":[],"title_canon_sha256":"ce7925250299b4323fabe8b53098aa2186947bbf21903d9b04c009b666103237","abstract_canon_sha256":"7b59a22e3b275286d9307564ecc079fe24418dffa4fee58b2d905061f57312a6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:38:47.089586Z","signature_b64":"WErQbF1yTlBLvKhlC2y6maMAgGjCQDr6YAqEIFUm1lDReoZ4+DhM96GtQeuRJeMGL8MO1vRttLE91wkjm0b4Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b536dbb8fd566310a0efa2fc1a159df7755b7ec510e50dd9712096c5ba60724","last_reissued_at":"2026-05-18T00:38:47.088964Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:38:47.088964Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchical Subtask Discovery With Non-Negative Matrix Factorization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Adam C. Earle, Andrew M. Saxe, Benjamin Rosman","submitted_at":"2017-08-01T18:19:40Z","abstract_excerpt":"Hierarchical reinforcement learning methods offer a powerful means of planning flexible behavior in complicated domains. However, learning an appropriate hierarchical decomposition of a domain into subtasks remains a substantial challenge. We present a novel algorithm for subtask discovery, based on the recently introduced multitask linearly-solvable Markov decision process (MLMDP) framework. The MLMDP can perform never-before-seen tasks by representing them as a linear combination of a previously learned basis set of tasks. In this setting, the subtask discovery problem can naturally be posed"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.00463","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":"1708.00463","created_at":"2026-05-18T00:38:47.089095+00:00"},{"alias_kind":"arxiv_version","alias_value":"1708.00463v1","created_at":"2026-05-18T00:38:47.089095+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.00463","created_at":"2026-05-18T00:38:47.089095+00:00"},{"alias_kind":"pith_short_12","alias_value":"DNJW3O4P2VTD","created_at":"2026-05-18T12:31:12.930513+00:00"},{"alias_kind":"pith_short_16","alias_value":"DNJW3O4P2VTDCCQO","created_at":"2026-05-18T12:31:12.930513+00:00"},{"alias_kind":"pith_short_8","alias_value":"DNJW3O4P","created_at":"2026-05-18T12:31:12.930513+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/DNJW3O4P2VTDCCQO7IX4DIKZ35","json":"https://pith.science/pith/DNJW3O4P2VTDCCQO7IX4DIKZ35.json","graph_json":"https://pith.science/api/pith-number/DNJW3O4P2VTDCCQO7IX4DIKZ35/graph.json","events_json":"https://pith.science/api/pith-number/DNJW3O4P2VTDCCQO7IX4DIKZ35/events.json","paper":"https://pith.science/paper/DNJW3O4P"},"agent_actions":{"view_html":"https://pith.science/pith/DNJW3O4P2VTDCCQO7IX4DIKZ35","download_json":"https://pith.science/pith/DNJW3O4P2VTDCCQO7IX4DIKZ35.json","view_paper":"https://pith.science/paper/DNJW3O4P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1708.00463&json=true","fetch_graph":"https://pith.science/api/pith-number/DNJW3O4P2VTDCCQO7IX4DIKZ35/graph.json","fetch_events":"https://pith.science/api/pith-number/DNJW3O4P2VTDCCQO7IX4DIKZ35/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DNJW3O4P2VTDCCQO7IX4DIKZ35/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DNJW3O4P2VTDCCQO7IX4DIKZ35/action/storage_attestation","attest_author":"https://pith.science/pith/DNJW3O4P2VTDCCQO7IX4DIKZ35/action/author_attestation","sign_citation":"https://pith.science/pith/DNJW3O4P2VTDCCQO7IX4DIKZ35/action/citation_signature","submit_replication":"https://pith.science/pith/DNJW3O4P2VTDCCQO7IX4DIKZ35/action/replication_record"}},"created_at":"2026-05-18T00:38:47.089095+00:00","updated_at":"2026-05-18T00:38:47.089095+00:00"}