{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:IEFT6V5YMMLDCYLE635JCK3BZN","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":"65397b423d4ce1b9449c90814d0df087ac6f512e382c3761050e66a08411f1e0","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-06-24T15:40:57Z","title_canon_sha256":"4654f2d896afaa147810f4872fd16098c3f98b77c7b45f87e279923f13ecf43f"},"schema_version":"1.0","source":{"id":"2106.13105","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.13105","created_at":"2026-07-05T02:52:09Z"},{"alias_kind":"arxiv_version","alias_value":"2106.13105v1","created_at":"2026-07-05T02:52:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.13105","created_at":"2026-07-05T02:52:09Z"},{"alias_kind":"pith_short_12","alias_value":"IEFT6V5YMMLD","created_at":"2026-07-05T02:52:09Z"},{"alias_kind":"pith_short_16","alias_value":"IEFT6V5YMMLDCYLE","created_at":"2026-07-05T02:52:09Z"},{"alias_kind":"pith_short_8","alias_value":"IEFT6V5Y","created_at":"2026-07-05T02:52:09Z"}],"graph_snapshots":[{"event_id":"sha256:3825d1e61355d7e286dbb45d582d2ef50027f64d39a485e3a794cf60322d93bc","target":"graph","created_at":"2026-07-05T02:52:09Z","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/2106.13105/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-06-24T15:40:57Z","title":"The Option Keyboard: Combining Skills in Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.13105","kind":"arxiv","version":1},"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":"sha256:7763d3c72061235f2db42ae1843325b2b4052ca42134ab93c9aacc5789c66fc7","target":"record","created_at":"2026-07-05T02:52:09Z","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":"65397b423d4ce1b9449c90814d0df087ac6f512e382c3761050e66a08411f1e0","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2021-06-24T15:40:57Z","title_canon_sha256":"4654f2d896afaa147810f4872fd16098c3f98b77c7b45f87e279923f13ecf43f"},"schema_version":"1.0","source":{"id":"2106.13105","kind":"arxiv","version":1}},"canonical_sha256":"410b3f57b86316316164f6fa912b61cb6980217517a85b19bbaa3911bfc01f2d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"410b3f57b86316316164f6fa912b61cb6980217517a85b19bbaa3911bfc01f2d","first_computed_at":"2026-07-05T02:52:09.699804Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:52:09.699804Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0IFzi8U1mB0r1jKNx0oKqhl24D+/csE3k+JEp3aU8IntlDJc00DlO+9IaTDxtEOpLGKse5tRSXHVAgQBXK4MAA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:52:09.700263Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.13105","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7763d3c72061235f2db42ae1843325b2b4052ca42134ab93c9aacc5789c66fc7","sha256:3825d1e61355d7e286dbb45d582d2ef50027f64d39a485e3a794cf60322d93bc"],"state_sha256":"0c75a12268c8bb80a390795457e66e3bf2be928e8753b0ee19f95ba95ac2b04f"}