{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:364JZSBF4MZXCONKUSKHX3JQI7","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":"363a650baabf92e90a79783f9de1b2b9593cd73777e77bfbf0aeaee4e53cecab","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-15T01:34:27Z","title_canon_sha256":"26954da707bafd3f4825f621f189f0e35cf87c32d84e887df884796f5e4dfaca"},"schema_version":"1.0","source":{"id":"1809.05630","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.05630","created_at":"2026-05-18T00:00:39Z"},{"alias_kind":"arxiv_version","alias_value":"1809.05630v2","created_at":"2026-05-18T00:00:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.05630","created_at":"2026-05-18T00:00:39Z"},{"alias_kind":"pith_short_12","alias_value":"364JZSBF4MZX","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"364JZSBF4MZXCONK","created_at":"2026-05-18T12:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"364JZSBF","created_at":"2026-05-18T12:32:02Z"}],"graph_snapshots":[{"event_id":"sha256:dc2f6a1927bed45f4439f8b5815406bdcd132b81c95af97289f55ca8187c709c","target":"graph","created_at":"2026-05-18T00:00:39Z","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 techniques have demonstrated superior performance in a wide variety of environments. As improvements in training algorithms continue at a brisk pace, theoretical or empirical studies on understanding what these networks seem to learn, are far behind. In this paper we propose an interpretable neural network architecture for Q-learning which provides a global explanation of the model's behavior using key-value memories, attention and reconstructible embeddings. With a directed exploration strategy, our model can reach training rewards comparable to the state-of-the-ar","authors_text":"Katia Sycara, Raghuram Mandyam Annasamy","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-15T01:34:27Z","title":"Towards Better Interpretability in Deep Q-Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.05630","kind":"arxiv","version":2},"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:ee0a6b1d32b69fdb13435a8bf324355717570002bbe0ae62c152557d00330799","target":"record","created_at":"2026-05-18T00:00:39Z","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":"363a650baabf92e90a79783f9de1b2b9593cd73777e77bfbf0aeaee4e53cecab","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-15T01:34:27Z","title_canon_sha256":"26954da707bafd3f4825f621f189f0e35cf87c32d84e887df884796f5e4dfaca"},"schema_version":"1.0","source":{"id":"1809.05630","kind":"arxiv","version":2}},"canonical_sha256":"dfb89cc825e3337139aaa4947bed3047cbac339b172821b0380e89e8b2c57c41","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dfb89cc825e3337139aaa4947bed3047cbac339b172821b0380e89e8b2c57c41","first_computed_at":"2026-05-18T00:00:39.272117Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:00:39.272117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"B4VhZGpQqbmE8MIBzCnjH33kTwej/Tf/bYBMiATmJwb5m89FXdPWV1ozaNsM+WzsjYtMlyYEN6yI1dv0iYjrDw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:00:39.272611Z","signed_message":"canonical_sha256_bytes"},"source_id":"1809.05630","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ee0a6b1d32b69fdb13435a8bf324355717570002bbe0ae62c152557d00330799","sha256:dc2f6a1927bed45f4439f8b5815406bdcd132b81c95af97289f55ca8187c709c"],"state_sha256":"f653cc7a26fe2ad01ba509bf5604c21fc312f6c0b6d5f6a8cd7cbdd63bed3846"}