{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:7N7K4G5NOOW7ISP2RJNQMDH6WT","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":"004940a426688b205028f0d8c09a793893f6c66337157466edbbb84777f5cf93","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-31T11:12:31Z","title_canon_sha256":"7e4f7b292608148a7311d216102a812c0fa3682bd4657446021b2080f0adb5c6"},"schema_version":"1.0","source":{"id":"2607.29294","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.29294","created_at":"2026-08-03T01:23:58Z"},{"alias_kind":"arxiv_version","alias_value":"2607.29294v1","created_at":"2026-08-03T01:23:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.29294","created_at":"2026-08-03T01:23:58Z"},{"alias_kind":"pith_short_12","alias_value":"7N7K4G5NOOW7","created_at":"2026-08-03T01:23:58Z"},{"alias_kind":"pith_short_16","alias_value":"7N7K4G5NOOW7ISP2","created_at":"2026-08-03T01:23:58Z"},{"alias_kind":"pith_short_8","alias_value":"7N7K4G5N","created_at":"2026-08-03T01:23:58Z"}],"graph_snapshots":[{"event_id":"sha256:002fbba924cc1f51c61f91454ea49d264bb7a5491bed9442987d743541dd3cd4","target":"graph","created_at":"2026-08-03T01:23:58Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2607.29294/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present HBPI-UCRL, a model-based algorithm for hierarchical reinforcement learning (HRL) that learns high-level and low-level policies in parallel. HBPI-UCRL exploits the fact that a high-level transition corresponds to a multi-step transition at the low level. We introduce two conditions on the low-level dynamics that are sufficient to make parallel HRL learnable. When these conditions hold, we prove that HBPI-UCRL has a polynomial sample complexity in the problem parameters. In the sparse-reward, goal-directed setting, our sample complexity upper bound for HBPI-UCRL is strictly lower than","authors_text":"Anders Jonsson, Emilie Kaufmann, Gianmarco Tedeschi, Lorenzo Steccanella","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-31T11:12:31Z","title":"Sample Efficient Hierarchical Reinforcement Learning via Best Policy Identification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.29294","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:c72aac895045674f1bceae27aed68832d9135b0c0c3a064269a16c01975ea98d","target":"record","created_at":"2026-08-03T01:23:58Z","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":"004940a426688b205028f0d8c09a793893f6c66337157466edbbb84777f5cf93","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-31T11:12:31Z","title_canon_sha256":"7e4f7b292608148a7311d216102a812c0fa3682bd4657446021b2080f0adb5c6"},"schema_version":"1.0","source":{"id":"2607.29294","kind":"arxiv","version":1}},"canonical_sha256":"fb7eae1bad73adf449fa8a5b060cfeb4e04858f811fe580e04baab0b3b17e252","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fb7eae1bad73adf449fa8a5b060cfeb4e04858f811fe580e04baab0b3b17e252","first_computed_at":"2026-08-03T01:23:58.919866Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-03T01:23:58.919866Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DtH1+3A/XgIV4fMDbdK7XkaAFhcFu+j02rjVuhXfA2j6MDPGnAiS1837c/NdJWJPzGosGtOdEc8yy8wfsOppBg==","signature_status":"signed_v1","signed_at":"2026-08-03T01:23:58.921665Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.29294","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c72aac895045674f1bceae27aed68832d9135b0c0c3a064269a16c01975ea98d","sha256:002fbba924cc1f51c61f91454ea49d264bb7a5491bed9442987d743541dd3cd4"],"state_sha256":"c6caf9772d4426bec98ced2c2aa6e7579add980ab7d31f699349ee377a3b364b"}