{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:A4U4XUKH4J5QKX6HMS4EVPF26U","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":"41c210fd30a4e57789081a958326cf04dac221e4000bca1bf7254300e4412ad1","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-12T06:43:12Z","title_canon_sha256":"5ab15be0bcae740d8346e63979392f264e68936e0c86ca281d8958fb969af71c"},"schema_version":"1.0","source":{"id":"1807.04439","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.04439","created_at":"2026-05-18T00:10:53Z"},{"alias_kind":"arxiv_version","alias_value":"1807.04439v1","created_at":"2026-05-18T00:10:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.04439","created_at":"2026-05-18T00:10:53Z"},{"alias_kind":"pith_short_12","alias_value":"A4U4XUKH4J5Q","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"A4U4XUKH4J5QKX6H","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"A4U4XUKH","created_at":"2026-05-18T12:32:13Z"}],"graph_snapshots":[{"event_id":"sha256:268327004b94a707906ec6c18ec489a214a64bf5cc010b34a8a8856d89ebce45","target":"graph","created_at":"2026-05-18T00:10:53Z","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"},"paper":{"abstract_excerpt":"An important property for lifelong-learning agents is the ability to combine existing skills to solve unseen tasks. In general, however, it is unclear how to compose skills in a principled way. We provide a \"recipe\" for optimal value function composition in entropy-regularised reinforcement learning (RL) and then extend this to the standard RL setting. Composition is demonstrated in a video game environment, where an agent with an existing library of policies is able to solve new tasks without the need for further learning.","authors_text":"Adam Earle, Benjamin Rosman, Benjamin van Niekerk, Steven James","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-12T06:43:12Z","title":"Will it Blend? Composing Value Functions in Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.04439","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":"sha256:9faf414fd8303cf7d19672728cfb025f94c7260d207901c137d6ecbdc3584537","target":"record","created_at":"2026-05-18T00:10:53Z","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":"41c210fd30a4e57789081a958326cf04dac221e4000bca1bf7254300e4412ad1","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-12T06:43:12Z","title_canon_sha256":"5ab15be0bcae740d8346e63979392f264e68936e0c86ca281d8958fb969af71c"},"schema_version":"1.0","source":{"id":"1807.04439","kind":"arxiv","version":1}},"canonical_sha256":"0729cbd147e27b055fc764b84abcbaf52ffbea23b22046ab91ff61f291df29ad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0729cbd147e27b055fc764b84abcbaf52ffbea23b22046ab91ff61f291df29ad","first_computed_at":"2026-05-18T00:10:53.520009Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:10:53.520009Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VrMRdn8PMlLDvw2GNRzL0xT7VZb8JER8eaD5E1+kCN3CXUpI7Tuj/K9a4JEvMhdItAfnxFs9KDoDQIFMxvbTAA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:10:53.520716Z","signed_message":"canonical_sha256_bytes"},"source_id":"1807.04439","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9faf414fd8303cf7d19672728cfb025f94c7260d207901c137d6ecbdc3584537","sha256:268327004b94a707906ec6c18ec489a214a64bf5cc010b34a8a8856d89ebce45"],"state_sha256":"22e97f2135833de0ed0b19b9e7fa22b6de2475482b23e4df5546d672da39589f"}