{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:4QFJNZI4L4ZLI5WDZK2NEODJ63","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":"d848d28e9e4d71fa3f0d458c9815631e696a738291cc39cc0fd52702120d2f23","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-14T09:24:32Z","title_canon_sha256":"4ead6ab98bc3847cb68073720ef050c8c4a3bf953bb3282986b19baac647a8da"},"schema_version":"1.0","source":{"id":"2306.08388","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.08388","created_at":"2026-07-05T08:42:52Z"},{"alias_kind":"arxiv_version","alias_value":"2306.08388v3","created_at":"2026-07-05T08:42:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.08388","created_at":"2026-07-05T08:42:52Z"},{"alias_kind":"pith_short_12","alias_value":"4QFJNZI4L4ZL","created_at":"2026-07-05T08:42:52Z"},{"alias_kind":"pith_short_16","alias_value":"4QFJNZI4L4ZLI5WD","created_at":"2026-07-05T08:42:52Z"},{"alias_kind":"pith_short_8","alias_value":"4QFJNZI4","created_at":"2026-07-05T08:42:52Z"}],"graph_snapshots":[{"event_id":"sha256:c9687dc8eb8edb3242d9e9b6305e71bbda66a1913a2760f57d96b6c5cebf8134","target":"graph","created_at":"2026-07-05T08:42:52Z","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/2306.08388/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Hierarchical reinforcement learning (RL) can accelerate long-horizon decision-making by temporally abstracting a policy into multiple levels. Promising results in sparse reward environments have been seen with skills, i.e. sequences of primitive actions. Typically, a skill latent space and policy are discovered from offline data. However, the resulting low-level policy can be unreliable due to low-coverage demonstrations or distribution shifts. As a solution, we propose the Skill-Critic algorithm to fine-tune the low-level policy in conjunction with high-level skill selection. Our Skill-Critic","authors_text":"Catherine Weaver, Ce Hao, Chen Tang, Kenta Kawamoto, Masayoshi Tomizuka, Wei Zhan","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-14T09:24:32Z","title":"Skill-Critic: Refining Learned Skills for Hierarchical Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.08388","kind":"arxiv","version":3},"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":"sha256:68f67847655bf2b26dfa249ebfabe8f2c166c369227b8f61ec7898f62ccd9079","target":"record","created_at":"2026-07-05T08:42:52Z","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":"d848d28e9e4d71fa3f0d458c9815631e696a738291cc39cc0fd52702120d2f23","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-14T09:24:32Z","title_canon_sha256":"4ead6ab98bc3847cb68073720ef050c8c4a3bf953bb3282986b19baac647a8da"},"schema_version":"1.0","source":{"id":"2306.08388","kind":"arxiv","version":3}},"canonical_sha256":"e40a96e51c5f32b476c3cab4d23869f6f9d3dde8687649f1709d2ee910b6c714","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e40a96e51c5f32b476c3cab4d23869f6f9d3dde8687649f1709d2ee910b6c714","first_computed_at":"2026-07-05T08:42:52.883560Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:42:52.883560Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rSB9TZTMOk3RsKwCuhIDKCHrhJtqlaHvP0MiBsY5ALX93kyRNnAifhLrHJCyHiqNCxvMhlZg6KqiPzm6xhwCDA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:42:52.883927Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.08388","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:68f67847655bf2b26dfa249ebfabe8f2c166c369227b8f61ec7898f62ccd9079","sha256:c9687dc8eb8edb3242d9e9b6305e71bbda66a1913a2760f57d96b6c5cebf8134"],"state_sha256":"7923023bb576a38b12e24b833ab6db7ba39286ed349ae942685829bc5d427e4b"}