{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:LYJLTPDPVHQEMKFBLL2GE47SP4","short_pith_number":"pith:LYJLTPDP","schema_version":"1.0","canonical_sha256":"5e12b9bc6fa9e04628a15af46273f27f249fa77239774c8f1cd5fe8b06e8f239","source":{"kind":"arxiv","id":"1906.05862","version":4},"attestation_state":"computed","paper":{"title":"Sub-policy Adaptation for Hierarchical Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander C. Li, Carlos Florensa, Ignasi Clavera, Pieter Abbeel","submitted_at":"2019-06-13T16:59:48Z","abstract_excerpt":"Hierarchical reinforcement learning is a promising approach to tackle long-horizon decision-making problems with sparse rewards. Unfortunately, most methods still decouple the lower-level skill acquisition process and the training of a higher level that controls the skills in a new task. Leaving the skills fixed can lead to significant sub-optimality in the transfer setting. In this work, we propose a novel algorithm to discover a set of skills, and continuously adapt them along with the higher level even when training on a new task. Our main contributions are two-fold. First, we derive a new "},"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":"1906.05862","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-13T16:59:48Z","cross_cats_sorted":["cs.AI","cs.NE","stat.ML"],"title_canon_sha256":"df4b7422517b106c7ecd9bd677cedd6d96e14c4200770d6b18bc30f60491a964","abstract_canon_sha256":"7858b9448ab5ffb8f5fc7fe298486fa705478b0fd98f9fff8f320f53347fde41"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:02:43.434083Z","signature_b64":"R4MWikFaEcp5aPa8uQ57cwt5yY+KllTRXYTrVeaT+u7UXci+ppn3JZy+vCMUw+0gVWgNv3Ahpj8fzGMo4pJwBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e12b9bc6fa9e04628a15af46273f27f249fa77239774c8f1cd5fe8b06e8f239","last_reissued_at":"2026-07-05T01:02:43.433620Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:02:43.433620Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sub-policy Adaptation for Hierarchical Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander C. Li, Carlos Florensa, Ignasi Clavera, Pieter Abbeel","submitted_at":"2019-06-13T16:59:48Z","abstract_excerpt":"Hierarchical reinforcement learning is a promising approach to tackle long-horizon decision-making problems with sparse rewards. Unfortunately, most methods still decouple the lower-level skill acquisition process and the training of a higher level that controls the skills in a new task. Leaving the skills fixed can lead to significant sub-optimality in the transfer setting. In this work, we propose a novel algorithm to discover a set of skills, and continuously adapt them along with the higher level even when training on a new task. Our main contributions are two-fold. First, we derive a new "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.05862","kind":"arxiv","version":4},"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/1906.05862/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":"1906.05862","created_at":"2026-07-05T01:02:43.433674+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.05862v4","created_at":"2026-07-05T01:02:43.433674+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.05862","created_at":"2026-07-05T01:02:43.433674+00:00"},{"alias_kind":"pith_short_12","alias_value":"LYJLTPDPVHQE","created_at":"2026-07-05T01:02:43.433674+00:00"},{"alias_kind":"pith_short_16","alias_value":"LYJLTPDPVHQEMKFB","created_at":"2026-07-05T01:02:43.433674+00:00"},{"alias_kind":"pith_short_8","alias_value":"LYJLTPDP","created_at":"2026-07-05T01:02:43.433674+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.24558","citing_title":"Hierarchical Behaviour Spaces","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LYJLTPDPVHQEMKFBLL2GE47SP4","json":"https://pith.science/pith/LYJLTPDPVHQEMKFBLL2GE47SP4.json","graph_json":"https://pith.science/api/pith-number/LYJLTPDPVHQEMKFBLL2GE47SP4/graph.json","events_json":"https://pith.science/api/pith-number/LYJLTPDPVHQEMKFBLL2GE47SP4/events.json","paper":"https://pith.science/paper/LYJLTPDP"},"agent_actions":{"view_html":"https://pith.science/pith/LYJLTPDPVHQEMKFBLL2GE47SP4","download_json":"https://pith.science/pith/LYJLTPDPVHQEMKFBLL2GE47SP4.json","view_paper":"https://pith.science/paper/LYJLTPDP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.05862&json=true","fetch_graph":"https://pith.science/api/pith-number/LYJLTPDPVHQEMKFBLL2GE47SP4/graph.json","fetch_events":"https://pith.science/api/pith-number/LYJLTPDPVHQEMKFBLL2GE47SP4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LYJLTPDPVHQEMKFBLL2GE47SP4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LYJLTPDPVHQEMKFBLL2GE47SP4/action/storage_attestation","attest_author":"https://pith.science/pith/LYJLTPDPVHQEMKFBLL2GE47SP4/action/author_attestation","sign_citation":"https://pith.science/pith/LYJLTPDPVHQEMKFBLL2GE47SP4/action/citation_signature","submit_replication":"https://pith.science/pith/LYJLTPDPVHQEMKFBLL2GE47SP4/action/replication_record"}},"created_at":"2026-07-05T01:02:43.433674+00:00","updated_at":"2026-07-05T01:02:43.433674+00:00"}