{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:3MAQIEWVFX5R62ADLOXRTGKG7E","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"f4608591675e44982d072c3214693adf92ac03bcbea9d63b79fc52c21958320e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-03-10T13:50:31Z","title_canon_sha256":"dc3847f1a56235cf41f5a7d08f3095f70e599d9682e8f442f86727d7336da332"},"schema_version":"1.0","source":{"id":"1603.03267","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1603.03267","created_at":"2026-05-18T01:19:16Z"},{"alias_kind":"arxiv_version","alias_value":"1603.03267v1","created_at":"2026-05-18T01:19:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1603.03267","created_at":"2026-05-18T01:19:16Z"},{"alias_kind":"pith_short_12","alias_value":"3MAQIEWVFX5R","created_at":"2026-05-18T12:29:55Z"},{"alias_kind":"pith_short_16","alias_value":"3MAQIEWVFX5R62AD","created_at":"2026-05-18T12:29:55Z"},{"alias_kind":"pith_short_8","alias_value":"3MAQIEWV","created_at":"2026-05-18T12:29:55Z"}],"graph_snapshots":[{"event_id":"sha256:307d33173f86dd4b62bb51f2d41cd747f7ed8bcc4090b4a6da41e687985d42ab","target":"graph","created_at":"2026-05-18T01:19:16Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Anders Jonsson, Vicen\\c{c} G\\'omez","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-03-10T13:50:31Z","title":"Hierarchical Linearly-Solvable Markov Decision Problems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1603.03267","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:cdc37f802395413a099e98600442dfb51e2d911a7dce17b89e9a29a1b7d34b68","target":"record","created_at":"2026-05-18T01:19:16Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"f4608591675e44982d072c3214693adf92ac03bcbea9d63b79fc52c21958320e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-03-10T13:50:31Z","title_canon_sha256":"dc3847f1a56235cf41f5a7d08f3095f70e599d9682e8f442f86727d7336da332"},"schema_version":"1.0","source":{"id":"1603.03267","kind":"arxiv","version":1}},"canonical_sha256":"db010412d52dfb1f68035baf199946f9160b84fe94128606ce19f62d2c547ec4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"db010412d52dfb1f68035baf199946f9160b84fe94128606ce19f62d2c547ec4","first_computed_at":"2026-05-18T01:19:16.699069Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:19:16.699069Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZW3h7CCTtfBsBCaHCT3eWorIQ/QkZVAi1O+SOMXiA8v6wOn8PEyoGTY3cRtVqkp7xraaQeK6d84Ekb0S7tzDDw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:19:16.699457Z","signed_message":"canonical_sha256_bytes"},"source_id":"1603.03267","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cdc37f802395413a099e98600442dfb51e2d911a7dce17b89e9a29a1b7d34b68","sha256:307d33173f86dd4b62bb51f2d41cd747f7ed8bcc4090b4a6da41e687985d42ab"],"state_sha256":"f13faf2e33f19cf429a9fbcce585f1619b4832959aa7f4dca2405b3ebaa58a83"}