{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:5KBVHWZDGM6KGPQXWX6LCJ5K5H","short_pith_number":"pith:5KBVHWZD","schema_version":"1.0","canonical_sha256":"ea8353db23333ca33e17b5fcb127aae9db31bacbaa004e4df5ee3960204b9187","source":{"kind":"arxiv","id":"2211.02231","version":1},"attestation_state":"computed","paper":{"title":"Residual Skill Policies: Learning an Adaptable Skill-based Action Space for Reinforcement Learning for Robotics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Brendan Tidd, Krishan Rana, Michael Milford, Ming Xu, Niko S\\\"underhauf","submitted_at":"2022-11-04T02:42:17Z","abstract_excerpt":"Skill-based reinforcement learning (RL) has emerged as a promising strategy to leverage prior knowledge for accelerated robot learning. Skills are typically extracted from expert demonstrations and are embedded into a latent space from which they can be sampled as actions by a high-level RL agent. However, this skill space is expansive, and not all skills are relevant for a given robot state, making exploration difficult. Furthermore, the downstream RL agent is limited to learning structurally similar tasks to those used to construct the skill space. We firstly propose accelerating exploration"},"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":"2211.02231","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2022-11-04T02:42:17Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c1bc488f0567dc71b270f3558d42c3802e16ae6ec574aad0a0d05e846c1563df","abstract_canon_sha256":"bb95cb10d000df3dd95978851bce00eeb8818fd8d49d771c7b3bd395c9356a2e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:13:13.019730Z","signature_b64":"NnkxO6R0z18YjUW0C3bh+3QZ2XBKc1PGn0IjO7Jw5UagVFHjdfneaxp3zfkIfzanDuQBiDXhSWI55gz7eKPJBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea8353db23333ca33e17b5fcb127aae9db31bacbaa004e4df5ee3960204b9187","last_reissued_at":"2026-07-05T05:13:13.019394Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:13:13.019394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Residual Skill Policies: Learning an Adaptable Skill-based Action Space for Reinforcement Learning for Robotics","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Brendan Tidd, Krishan Rana, Michael Milford, Ming Xu, Niko S\\\"underhauf","submitted_at":"2022-11-04T02:42:17Z","abstract_excerpt":"Skill-based reinforcement learning (RL) has emerged as a promising strategy to leverage prior knowledge for accelerated robot learning. Skills are typically extracted from expert demonstrations and are embedded into a latent space from which they can be sampled as actions by a high-level RL agent. However, this skill space is expansive, and not all skills are relevant for a given robot state, making exploration difficult. Furthermore, the downstream RL agent is limited to learning structurally similar tasks to those used to construct the skill space. We firstly propose accelerating exploration"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.02231","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/2211.02231/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":"2211.02231","created_at":"2026-07-05T05:13:13.019454+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.02231v1","created_at":"2026-07-05T05:13:13.019454+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.02231","created_at":"2026-07-05T05:13:13.019454+00:00"},{"alias_kind":"pith_short_12","alias_value":"5KBVHWZDGM6K","created_at":"2026-07-05T05:13:13.019454+00:00"},{"alias_kind":"pith_short_16","alias_value":"5KBVHWZDGM6KGPQX","created_at":"2026-07-05T05:13:13.019454+00:00"},{"alias_kind":"pith_short_8","alias_value":"5KBVHWZD","created_at":"2026-07-05T05:13:13.019454+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/5KBVHWZDGM6KGPQXWX6LCJ5K5H","json":"https://pith.science/pith/5KBVHWZDGM6KGPQXWX6LCJ5K5H.json","graph_json":"https://pith.science/api/pith-number/5KBVHWZDGM6KGPQXWX6LCJ5K5H/graph.json","events_json":"https://pith.science/api/pith-number/5KBVHWZDGM6KGPQXWX6LCJ5K5H/events.json","paper":"https://pith.science/paper/5KBVHWZD"},"agent_actions":{"view_html":"https://pith.science/pith/5KBVHWZDGM6KGPQXWX6LCJ5K5H","download_json":"https://pith.science/pith/5KBVHWZDGM6KGPQXWX6LCJ5K5H.json","view_paper":"https://pith.science/paper/5KBVHWZD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.02231&json=true","fetch_graph":"https://pith.science/api/pith-number/5KBVHWZDGM6KGPQXWX6LCJ5K5H/graph.json","fetch_events":"https://pith.science/api/pith-number/5KBVHWZDGM6KGPQXWX6LCJ5K5H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5KBVHWZDGM6KGPQXWX6LCJ5K5H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5KBVHWZDGM6KGPQXWX6LCJ5K5H/action/storage_attestation","attest_author":"https://pith.science/pith/5KBVHWZDGM6KGPQXWX6LCJ5K5H/action/author_attestation","sign_citation":"https://pith.science/pith/5KBVHWZDGM6KGPQXWX6LCJ5K5H/action/citation_signature","submit_replication":"https://pith.science/pith/5KBVHWZDGM6KGPQXWX6LCJ5K5H/action/replication_record"}},"created_at":"2026-07-05T05:13:13.019454+00:00","updated_at":"2026-07-05T05:13:13.019454+00:00"}