{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:3MAQIEWVFX5R62ADLOXRTGKG7E","short_pith_number":"pith:3MAQIEWV","schema_version":"1.0","canonical_sha256":"db010412d52dfb1f68035baf199946f9160b84fe94128606ce19f62d2c547ec4","source":{"kind":"arxiv","id":"1603.03267","version":1},"attestation_state":"computed","paper":{"title":"Hierarchical Linearly-Solvable Markov Decision Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Anders Jonsson, Vicen\\c{c} G\\'omez","submitted_at":"2016-03-10T13:50:31Z","abstract_excerpt":"We present a hierarchical reinforcement learning framework that formulates each task in the hierarchy as a special type of Markov decision process for which the Bellman equation is linear and has analytical solution. Problems of this type, called linearly-solvable MDPs (LMDPs) have interesting properties that can be exploited in a hierarchical setting, such as efficient learning of the optimal value function or task compositionality. The proposed hierarchical approach can also be seen as a novel alternative to solving LMDPs with large state spaces. We derive a hierarchical version of the so-ca"},"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":"1603.03267","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-03-10T13:50:31Z","cross_cats_sorted":[],"title_canon_sha256":"dc3847f1a56235cf41f5a7d08f3095f70e599d9682e8f442f86727d7336da332","abstract_canon_sha256":"f4608591675e44982d072c3214693adf92ac03bcbea9d63b79fc52c21958320e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:19:16.699457Z","signature_b64":"ZW3h7CCTtfBsBCaHCT3eWorIQ/QkZVAi1O+SOMXiA8v6wOn8PEyoGTY3cRtVqkp7xraaQeK6d84Ekb0S7tzDDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db010412d52dfb1f68035baf199946f9160b84fe94128606ce19f62d2c547ec4","last_reissued_at":"2026-05-18T01:19:16.699069Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:19:16.699069Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchical Linearly-Solvable Markov Decision Problems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Anders Jonsson, Vicen\\c{c} G\\'omez","submitted_at":"2016-03-10T13:50:31Z","abstract_excerpt":"We present a hierarchical reinforcement learning framework that formulates each task in the hierarchy as a special type of Markov decision process for which the Bellman equation is linear and has analytical solution. Problems of this type, called linearly-solvable MDPs (LMDPs) have interesting properties that can be exploited in a hierarchical setting, such as efficient learning of the optimal value function or task compositionality. The proposed hierarchical approach can also be seen as a novel alternative to solving LMDPs with large state spaces. We derive a hierarchical version of the so-ca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1603.03267","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":"1603.03267","created_at":"2026-05-18T01:19:16.699127+00:00"},{"alias_kind":"arxiv_version","alias_value":"1603.03267v1","created_at":"2026-05-18T01:19:16.699127+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1603.03267","created_at":"2026-05-18T01:19:16.699127+00:00"},{"alias_kind":"pith_short_12","alias_value":"3MAQIEWVFX5R","created_at":"2026-05-18T12:29:55.572404+00:00"},{"alias_kind":"pith_short_16","alias_value":"3MAQIEWVFX5R62AD","created_at":"2026-05-18T12:29:55.572404+00:00"},{"alias_kind":"pith_short_8","alias_value":"3MAQIEWV","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/3MAQIEWVFX5R62ADLOXRTGKG7E","json":"https://pith.science/pith/3MAQIEWVFX5R62ADLOXRTGKG7E.json","graph_json":"https://pith.science/api/pith-number/3MAQIEWVFX5R62ADLOXRTGKG7E/graph.json","events_json":"https://pith.science/api/pith-number/3MAQIEWVFX5R62ADLOXRTGKG7E/events.json","paper":"https://pith.science/paper/3MAQIEWV"},"agent_actions":{"view_html":"https://pith.science/pith/3MAQIEWVFX5R62ADLOXRTGKG7E","download_json":"https://pith.science/pith/3MAQIEWVFX5R62ADLOXRTGKG7E.json","view_paper":"https://pith.science/paper/3MAQIEWV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1603.03267&json=true","fetch_graph":"https://pith.science/api/pith-number/3MAQIEWVFX5R62ADLOXRTGKG7E/graph.json","fetch_events":"https://pith.science/api/pith-number/3MAQIEWVFX5R62ADLOXRTGKG7E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3MAQIEWVFX5R62ADLOXRTGKG7E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3MAQIEWVFX5R62ADLOXRTGKG7E/action/storage_attestation","attest_author":"https://pith.science/pith/3MAQIEWVFX5R62ADLOXRTGKG7E/action/author_attestation","sign_citation":"https://pith.science/pith/3MAQIEWVFX5R62ADLOXRTGKG7E/action/citation_signature","submit_replication":"https://pith.science/pith/3MAQIEWVFX5R62ADLOXRTGKG7E/action/replication_record"}},"created_at":"2026-05-18T01:19:16.699127+00:00","updated_at":"2026-05-18T01:19:16.699127+00:00"}