{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:5DOJVOWXJYF5M7IM4SCTZGFOVA","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":"630867c3b3821c5b49822ec15d62c620a917e6f3337cc91480bc7db8ebbd3edc","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-16T14:31:35Z","title_canon_sha256":"16df01049bdcce9792002c8c260eb6c7889d4927d44a5deac08dac155b2615e5"},"schema_version":"1.0","source":{"id":"1807.05887","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.05887","created_at":"2026-05-18T00:10:42Z"},{"alias_kind":"arxiv_version","alias_value":"1807.05887v1","created_at":"2026-05-18T00:10:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.05887","created_at":"2026-05-18T00:10:42Z"},{"alias_kind":"pith_short_12","alias_value":"5DOJVOWXJYF5","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"5DOJVOWXJYF5M7IM","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"5DOJVOWX","created_at":"2026-05-18T12:32:08Z"}],"graph_snapshots":[{"event_id":"sha256:ac2cf9a1cbc9307876708cb7f9f9c974f41c90b73a91bb5b90ac9c4e5f52d879","target":"graph","created_at":"2026-05-18T00:10:42Z","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":"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","authors_text":"Guiliang Liu, Oliver Schulte, Qingcan Li, Wang Zhu","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-16T14:31:35Z","title":"Toward Interpretable Deep Reinforcement Learning with Linear Model U-Trees"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.05887","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:ff89c4b51fd470e074ba89e45f37b4546ea0d2c129e3807e08eac80b74d58047","target":"record","created_at":"2026-05-18T00:10:42Z","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":"630867c3b3821c5b49822ec15d62c620a917e6f3337cc91480bc7db8ebbd3edc","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-16T14:31:35Z","title_canon_sha256":"16df01049bdcce9792002c8c260eb6c7889d4927d44a5deac08dac155b2615e5"},"schema_version":"1.0","source":{"id":"1807.05887","kind":"arxiv","version":1}},"canonical_sha256":"e8dc9abad74e0bd67d0ce4853c98aea83c354b5b9a1f01eac65389903615e0ad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e8dc9abad74e0bd67d0ce4853c98aea83c354b5b9a1f01eac65389903615e0ad","first_computed_at":"2026-05-18T00:10:42.292066Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:10:42.292066Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"e0HnjzkU6kkOTL2WC7D3fo4Zi9BljtCjXtmHvdCVILFrrymNtFKE0mkR0rXOW8XQwO379vAlfIZSMcpnMH/CBg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:10:42.292683Z","signed_message":"canonical_sha256_bytes"},"source_id":"1807.05887","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ff89c4b51fd470e074ba89e45f37b4546ea0d2c129e3807e08eac80b74d58047","sha256:ac2cf9a1cbc9307876708cb7f9f9c974f41c90b73a91bb5b90ac9c4e5f52d879"],"state_sha256":"619b095faa1ec6134e5e0a3a1618a8e7e00ffa33d7a495ac7039ddf046c0c375"}