{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:IEFT6V5YMMLDCYLE635JCK3BZN","short_pith_number":"pith:IEFT6V5Y","schema_version":"1.0","canonical_sha256":"410b3f57b86316316164f6fa912b61cb6980217517a85b19bbaa3911bfc01f2d","source":{"kind":"arxiv","id":"2106.13105","version":1},"attestation_state":"computed","paper":{"title":"The Option Keyboard: Combining Skills in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Andr\\'e Barreto, Daniel Toyama, David Silver, Diana Borsa, Doina Precup, Eser Ayg\\\"un, Gheorghe Comanici, Jonathan Hunt, Philippe Hamel, Shaobo Hou, Shibl Mourad","submitted_at":"2021-06-24T15:40:57Z","abstract_excerpt":"The ability to combine known skills to create new ones may be crucial in the solution of complex reinforcement learning problems that unfold over extended periods. We argue that a robust way of combining skills is to define and manipulate them in the space of pseudo-rewards (or \"cumulants\"). Based on this premise, we propose a framework for combining skills using the formalism of options. We show that every deterministic option can be unambiguously represented as a cumulant defined in an extended domain. Building on this insight and on previous results on transfer learning, we show how to appr"},"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":"2106.13105","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-06-24T15:40:57Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4654f2d896afaa147810f4872fd16098c3f98b77c7b45f87e279923f13ecf43f","abstract_canon_sha256":"65397b423d4ce1b9449c90814d0df087ac6f512e382c3761050e66a08411f1e0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:52:09.700263Z","signature_b64":"0IFzi8U1mB0r1jKNx0oKqhl24D+/csE3k+JEp3aU8IntlDJc00DlO+9IaTDxtEOpLGKse5tRSXHVAgQBXK4MAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"410b3f57b86316316164f6fa912b61cb6980217517a85b19bbaa3911bfc01f2d","last_reissued_at":"2026-07-05T02:52:09.699804Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:52:09.699804Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Option Keyboard: Combining Skills in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Andr\\'e Barreto, Daniel Toyama, David Silver, Diana Borsa, Doina Precup, Eser Ayg\\\"un, Gheorghe Comanici, Jonathan Hunt, Philippe Hamel, Shaobo Hou, Shibl Mourad","submitted_at":"2021-06-24T15:40:57Z","abstract_excerpt":"The ability to combine known skills to create new ones may be crucial in the solution of complex reinforcement learning problems that unfold over extended periods. We argue that a robust way of combining skills is to define and manipulate them in the space of pseudo-rewards (or \"cumulants\"). Based on this premise, we propose a framework for combining skills using the formalism of options. We show that every deterministic option can be unambiguously represented as a cumulant defined in an extended domain. Building on this insight and on previous results on transfer learning, we show how to appr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.13105","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/2106.13105/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":"2106.13105","created_at":"2026-07-05T02:52:09.699857+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.13105v1","created_at":"2026-07-05T02:52:09.699857+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.13105","created_at":"2026-07-05T02:52:09.699857+00:00"},{"alias_kind":"pith_short_12","alias_value":"IEFT6V5YMMLD","created_at":"2026-07-05T02:52:09.699857+00:00"},{"alias_kind":"pith_short_16","alias_value":"IEFT6V5YMMLDCYLE","created_at":"2026-07-05T02:52:09.699857+00:00"},{"alias_kind":"pith_short_8","alias_value":"IEFT6V5Y","created_at":"2026-07-05T02:52:09.699857+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/IEFT6V5YMMLDCYLE635JCK3BZN","json":"https://pith.science/pith/IEFT6V5YMMLDCYLE635JCK3BZN.json","graph_json":"https://pith.science/api/pith-number/IEFT6V5YMMLDCYLE635JCK3BZN/graph.json","events_json":"https://pith.science/api/pith-number/IEFT6V5YMMLDCYLE635JCK3BZN/events.json","paper":"https://pith.science/paper/IEFT6V5Y"},"agent_actions":{"view_html":"https://pith.science/pith/IEFT6V5YMMLDCYLE635JCK3BZN","download_json":"https://pith.science/pith/IEFT6V5YMMLDCYLE635JCK3BZN.json","view_paper":"https://pith.science/paper/IEFT6V5Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.13105&json=true","fetch_graph":"https://pith.science/api/pith-number/IEFT6V5YMMLDCYLE635JCK3BZN/graph.json","fetch_events":"https://pith.science/api/pith-number/IEFT6V5YMMLDCYLE635JCK3BZN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IEFT6V5YMMLDCYLE635JCK3BZN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IEFT6V5YMMLDCYLE635JCK3BZN/action/storage_attestation","attest_author":"https://pith.science/pith/IEFT6V5YMMLDCYLE635JCK3BZN/action/author_attestation","sign_citation":"https://pith.science/pith/IEFT6V5YMMLDCYLE635JCK3BZN/action/citation_signature","submit_replication":"https://pith.science/pith/IEFT6V5YMMLDCYLE635JCK3BZN/action/replication_record"}},"created_at":"2026-07-05T02:52:09.699857+00:00","updated_at":"2026-07-05T02:52:09.699857+00:00"}