{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:A4U4XUKH4J5QKX6HMS4EVPF26U","short_pith_number":"pith:A4U4XUKH","schema_version":"1.0","canonical_sha256":"0729cbd147e27b055fc764b84abcbaf52ffbea23b22046ab91ff61f291df29ad","source":{"kind":"arxiv","id":"1807.04439","version":1},"attestation_state":"computed","paper":{"title":"Will it Blend? Composing Value Functions in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Adam Earle, Benjamin Rosman, Benjamin van Niekerk, Steven James","submitted_at":"2018-07-12T06:43:12Z","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."},"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":"1807.04439","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-12T06:43:12Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"5ab15be0bcae740d8346e63979392f264e68936e0c86ca281d8958fb969af71c","abstract_canon_sha256":"41c210fd30a4e57789081a958326cf04dac221e4000bca1bf7254300e4412ad1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:10:53.520716Z","signature_b64":"VrMRdn8PMlLDvw2GNRzL0xT7VZb8JER8eaD5E1+kCN3CXUpI7Tuj/K9a4JEvMhdItAfnxFs9KDoDQIFMxvbTAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0729cbd147e27b055fc764b84abcbaf52ffbea23b22046ab91ff61f291df29ad","last_reissued_at":"2026-05-18T00:10:53.520009Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:10:53.520009Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Will it Blend? Composing Value Functions in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Adam Earle, Benjamin Rosman, Benjamin van Niekerk, Steven James","submitted_at":"2018-07-12T06:43:12Z","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."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.04439","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":""},"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":"1807.04439","created_at":"2026-05-18T00:10:53.520115+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.04439v1","created_at":"2026-05-18T00:10:53.520115+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.04439","created_at":"2026-05-18T00:10:53.520115+00:00"},{"alias_kind":"pith_short_12","alias_value":"A4U4XUKH4J5Q","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_16","alias_value":"A4U4XUKH4J5QKX6H","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_8","alias_value":"A4U4XUKH","created_at":"2026-05-18T12:32:13.499390+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/A4U4XUKH4J5QKX6HMS4EVPF26U","json":"https://pith.science/pith/A4U4XUKH4J5QKX6HMS4EVPF26U.json","graph_json":"https://pith.science/api/pith-number/A4U4XUKH4J5QKX6HMS4EVPF26U/graph.json","events_json":"https://pith.science/api/pith-number/A4U4XUKH4J5QKX6HMS4EVPF26U/events.json","paper":"https://pith.science/paper/A4U4XUKH"},"agent_actions":{"view_html":"https://pith.science/pith/A4U4XUKH4J5QKX6HMS4EVPF26U","download_json":"https://pith.science/pith/A4U4XUKH4J5QKX6HMS4EVPF26U.json","view_paper":"https://pith.science/paper/A4U4XUKH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.04439&json=true","fetch_graph":"https://pith.science/api/pith-number/A4U4XUKH4J5QKX6HMS4EVPF26U/graph.json","fetch_events":"https://pith.science/api/pith-number/A4U4XUKH4J5QKX6HMS4EVPF26U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A4U4XUKH4J5QKX6HMS4EVPF26U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A4U4XUKH4J5QKX6HMS4EVPF26U/action/storage_attestation","attest_author":"https://pith.science/pith/A4U4XUKH4J5QKX6HMS4EVPF26U/action/author_attestation","sign_citation":"https://pith.science/pith/A4U4XUKH4J5QKX6HMS4EVPF26U/action/citation_signature","submit_replication":"https://pith.science/pith/A4U4XUKH4J5QKX6HMS4EVPF26U/action/replication_record"}},"created_at":"2026-05-18T00:10:53.520115+00:00","updated_at":"2026-05-18T00:10:53.520115+00:00"}