{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:S2EOHG5H3BNTAANGSJIFF3QCKL","short_pith_number":"pith:S2EOHG5H","schema_version":"1.0","canonical_sha256":"9688e39ba7d85b3001a6925052ee0252e773a8df7d368edafaebe53d7a70b959","source":{"kind":"arxiv","id":"2110.10809","version":1},"attestation_state":"computed","paper":{"title":"Hierarchical Skills for Efficient Exploration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Andreas Krause, Gabriel Synnaeve, Jonas Gehring, Nicolas Usunier","submitted_at":"2021-10-20T22:29:32Z","abstract_excerpt":"In reinforcement learning, pre-trained low-level skills have the potential to greatly facilitate exploration. However, prior knowledge of the downstream task is required to strike the right balance between generality (fine-grained control) and specificity (faster learning) in skill design. In previous work on continuous control, the sensitivity of methods to this trade-off has not been addressed explicitly, as locomotion provides a suitable prior for navigation tasks, which have been of foremost interest. In this work, we analyze this trade-off for low-level policy pre-training with a new benc"},"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":"2110.10809","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-20T22:29:32Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"208cef10a1f4ca835821d9fae463faec0a44409c4e46b62ac2b8965d26266771","abstract_canon_sha256":"0ea0d87f025499cd8105e67498cdc1b42eb79ab5dc1597cf530ed0784a3c1466"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:24:32.664402Z","signature_b64":"YtUr4juyuzLTYczCy7C69lldx1jxo2rQONqVWdg5HhNrhXXUGIKEmpMPwm8eTCHM9Vw5sNq91LCnBMzBuo+pBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9688e39ba7d85b3001a6925052ee0252e773a8df7d368edafaebe53d7a70b959","last_reissued_at":"2026-07-05T03:24:32.663665Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:24:32.663665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchical Skills for Efficient Exploration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Andreas Krause, Gabriel Synnaeve, Jonas Gehring, Nicolas Usunier","submitted_at":"2021-10-20T22:29:32Z","abstract_excerpt":"In reinforcement learning, pre-trained low-level skills have the potential to greatly facilitate exploration. However, prior knowledge of the downstream task is required to strike the right balance between generality (fine-grained control) and specificity (faster learning) in skill design. In previous work on continuous control, the sensitivity of methods to this trade-off has not been addressed explicitly, as locomotion provides a suitable prior for navigation tasks, which have been of foremost interest. In this work, we analyze this trade-off for low-level policy pre-training with a new benc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.10809","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2110.10809/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2110.10809","created_at":"2026-07-05T03:24:32.663912+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.10809v1","created_at":"2026-07-05T03:24:32.663912+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.10809","created_at":"2026-07-05T03:24:32.663912+00:00"},{"alias_kind":"pith_short_12","alias_value":"S2EOHG5H3BNT","created_at":"2026-07-05T03:24:32.663912+00:00"},{"alias_kind":"pith_short_16","alias_value":"S2EOHG5H3BNTAANG","created_at":"2026-07-05T03:24:32.663912+00:00"},{"alias_kind":"pith_short_8","alias_value":"S2EOHG5H","created_at":"2026-07-05T03:24:32.663912+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/S2EOHG5H3BNTAANGSJIFF3QCKL","json":"https://pith.science/pith/S2EOHG5H3BNTAANGSJIFF3QCKL.json","graph_json":"https://pith.science/api/pith-number/S2EOHG5H3BNTAANGSJIFF3QCKL/graph.json","events_json":"https://pith.science/api/pith-number/S2EOHG5H3BNTAANGSJIFF3QCKL/events.json","paper":"https://pith.science/paper/S2EOHG5H"},"agent_actions":{"view_html":"https://pith.science/pith/S2EOHG5H3BNTAANGSJIFF3QCKL","download_json":"https://pith.science/pith/S2EOHG5H3BNTAANGSJIFF3QCKL.json","view_paper":"https://pith.science/paper/S2EOHG5H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.10809&json=true","fetch_graph":"https://pith.science/api/pith-number/S2EOHG5H3BNTAANGSJIFF3QCKL/graph.json","fetch_events":"https://pith.science/api/pith-number/S2EOHG5H3BNTAANGSJIFF3QCKL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S2EOHG5H3BNTAANGSJIFF3QCKL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S2EOHG5H3BNTAANGSJIFF3QCKL/action/storage_attestation","attest_author":"https://pith.science/pith/S2EOHG5H3BNTAANGSJIFF3QCKL/action/author_attestation","sign_citation":"https://pith.science/pith/S2EOHG5H3BNTAANGSJIFF3QCKL/action/citation_signature","submit_replication":"https://pith.science/pith/S2EOHG5H3BNTAANGSJIFF3QCKL/action/replication_record"}},"created_at":"2026-07-05T03:24:32.663912+00:00","updated_at":"2026-07-05T03:24:32.663912+00:00"}