{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:5DOJVOWXJYF5M7IM4SCTZGFOVA","short_pith_number":"pith:5DOJVOWX","schema_version":"1.0","canonical_sha256":"e8dc9abad74e0bd67d0ce4853c98aea83c354b5b9a1f01eac65389903615e0ad","source":{"kind":"arxiv","id":"1807.05887","version":1},"attestation_state":"computed","paper":{"title":"Toward Interpretable Deep Reinforcement Learning with Linear Model U-Trees","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Guiliang Liu, Oliver Schulte, Qingcan Li, Wang Zhu","submitted_at":"2018-07-16T14:31:35Z","abstract_excerpt":"Deep Reinforcement Learning (DRL) has achieved impressive success in many applications. A key component of many DRL models is a neural network representing a Q function, to estimate the expected cumulative reward following a state-action pair. The Q function neural network contains a lot of implicit knowledge about the RL problems, but often remains unexamined and uninterpreted. To our knowledge, this work develops the first mimic learning framework for Q functions in DRL. We introduce Linear Model U-trees (LMUTs) to approximate neural network predictions. An LMUT is learned using a novel on-l"},"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":"1807.05887","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-16T14:31:35Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"16df01049bdcce9792002c8c260eb6c7889d4927d44a5deac08dac155b2615e5","abstract_canon_sha256":"630867c3b3821c5b49822ec15d62c620a917e6f3337cc91480bc7db8ebbd3edc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:10:42.292683Z","signature_b64":"e0HnjzkU6kkOTL2WC7D3fo4Zi9BljtCjXtmHvdCVILFrrymNtFKE0mkR0rXOW8XQwO379vAlfIZSMcpnMH/CBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e8dc9abad74e0bd67d0ce4853c98aea83c354b5b9a1f01eac65389903615e0ad","last_reissued_at":"2026-05-18T00:10:42.292066Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:10:42.292066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Toward Interpretable Deep Reinforcement Learning with Linear Model U-Trees","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Guiliang Liu, Oliver Schulte, Qingcan Li, Wang Zhu","submitted_at":"2018-07-16T14:31:35Z","abstract_excerpt":"Deep Reinforcement Learning (DRL) has achieved impressive success in many applications. A key component of many DRL models is a neural network representing a Q function, to estimate the expected cumulative reward following a state-action pair. The Q function neural network contains a lot of implicit knowledge about the RL problems, but often remains unexamined and uninterpreted. To our knowledge, this work develops the first mimic learning framework for Q functions in DRL. We introduce Linear Model U-trees (LMUTs) to approximate neural network predictions. An LMUT is learned using a novel on-l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.05887","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":"1807.05887","created_at":"2026-05-18T00:10:42.292151+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.05887v1","created_at":"2026-05-18T00:10:42.292151+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.05887","created_at":"2026-05-18T00:10:42.292151+00:00"},{"alias_kind":"pith_short_12","alias_value":"5DOJVOWXJYF5","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_16","alias_value":"5DOJVOWXJYF5M7IM","created_at":"2026-05-18T12:32:08.215937+00:00"},{"alias_kind":"pith_short_8","alias_value":"5DOJVOWX","created_at":"2026-05-18T12:32:08.215937+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/5DOJVOWXJYF5M7IM4SCTZGFOVA","json":"https://pith.science/pith/5DOJVOWXJYF5M7IM4SCTZGFOVA.json","graph_json":"https://pith.science/api/pith-number/5DOJVOWXJYF5M7IM4SCTZGFOVA/graph.json","events_json":"https://pith.science/api/pith-number/5DOJVOWXJYF5M7IM4SCTZGFOVA/events.json","paper":"https://pith.science/paper/5DOJVOWX"},"agent_actions":{"view_html":"https://pith.science/pith/5DOJVOWXJYF5M7IM4SCTZGFOVA","download_json":"https://pith.science/pith/5DOJVOWXJYF5M7IM4SCTZGFOVA.json","view_paper":"https://pith.science/paper/5DOJVOWX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.05887&json=true","fetch_graph":"https://pith.science/api/pith-number/5DOJVOWXJYF5M7IM4SCTZGFOVA/graph.json","fetch_events":"https://pith.science/api/pith-number/5DOJVOWXJYF5M7IM4SCTZGFOVA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5DOJVOWXJYF5M7IM4SCTZGFOVA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5DOJVOWXJYF5M7IM4SCTZGFOVA/action/storage_attestation","attest_author":"https://pith.science/pith/5DOJVOWXJYF5M7IM4SCTZGFOVA/action/author_attestation","sign_citation":"https://pith.science/pith/5DOJVOWXJYF5M7IM4SCTZGFOVA/action/citation_signature","submit_replication":"https://pith.science/pith/5DOJVOWXJYF5M7IM4SCTZGFOVA/action/replication_record"}},"created_at":"2026-05-18T00:10:42.292151+00:00","updated_at":"2026-05-18T00:10:42.292151+00:00"}