{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:LYJLTPDPVHQEMKFBLL2GE47SP4","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":"7858b9448ab5ffb8f5fc7fe298486fa705478b0fd98f9fff8f320f53347fde41","cross_cats_sorted":["cs.AI","cs.NE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-13T16:59:48Z","title_canon_sha256":"df4b7422517b106c7ecd9bd677cedd6d96e14c4200770d6b18bc30f60491a964"},"schema_version":"1.0","source":{"id":"1906.05862","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.05862","created_at":"2026-07-05T01:02:43Z"},{"alias_kind":"arxiv_version","alias_value":"1906.05862v4","created_at":"2026-07-05T01:02:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.05862","created_at":"2026-07-05T01:02:43Z"},{"alias_kind":"pith_short_12","alias_value":"LYJLTPDPVHQE","created_at":"2026-07-05T01:02:43Z"},{"alias_kind":"pith_short_16","alias_value":"LYJLTPDPVHQEMKFB","created_at":"2026-07-05T01:02:43Z"},{"alias_kind":"pith_short_8","alias_value":"LYJLTPDP","created_at":"2026-07-05T01:02:43Z"}],"graph_snapshots":[{"event_id":"sha256:b7bd45a3223c2135c7cb62c0ff5b035953c1064c6bf446a399e2ab1d78ffb5fe","target":"graph","created_at":"2026-07-05T01:02:43Z","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/1906.05862/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Alexander C. Li, Carlos Florensa, Ignasi Clavera, Pieter Abbeel","cross_cats":["cs.AI","cs.NE","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-13T16:59:48Z","title":"Sub-policy Adaptation for Hierarchical Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.05862","kind":"arxiv","version":4},"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":"sha256:9b42c993d9ac07ec907b021ba8a5b2a28ba144725d3bcf3867b090c5e7e59290","target":"record","created_at":"2026-07-05T01:02:43Z","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":"7858b9448ab5ffb8f5fc7fe298486fa705478b0fd98f9fff8f320f53347fde41","cross_cats_sorted":["cs.AI","cs.NE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-13T16:59:48Z","title_canon_sha256":"df4b7422517b106c7ecd9bd677cedd6d96e14c4200770d6b18bc30f60491a964"},"schema_version":"1.0","source":{"id":"1906.05862","kind":"arxiv","version":4}},"canonical_sha256":"5e12b9bc6fa9e04628a15af46273f27f249fa77239774c8f1cd5fe8b06e8f239","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5e12b9bc6fa9e04628a15af46273f27f249fa77239774c8f1cd5fe8b06e8f239","first_computed_at":"2026-07-05T01:02:43.433620Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:02:43.433620Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"R4MWikFaEcp5aPa8uQ57cwt5yY+KllTRXYTrVeaT+u7UXci+ppn3JZy+vCMUw+0gVWgNv3Ahpj8fzGMo4pJwBw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:02:43.434083Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.05862","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9b42c993d9ac07ec907b021ba8a5b2a28ba144725d3bcf3867b090c5e7e59290","sha256:b7bd45a3223c2135c7cb62c0ff5b035953c1064c6bf446a399e2ab1d78ffb5fe"],"state_sha256":"b949710c015d87260b16355e33735dbfee98da041bd9feab2de5e4d1f6b38fbf"}