{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:O4ONZ33JIDYQPO2OEDTNV7ERKY","short_pith_number":"pith:O4ONZ33J","canonical_record":{"source":{"id":"1803.07482","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-20T15:22:52Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"0bd50232f4e96163bae28d4b782f71e155eb5414d2afcdfe538434d2bd7cdc5d","abstract_canon_sha256":"a510519c486998ee74daef6b4e9456e3c920e5f5d7ed903b53a893e20a202a8a"},"schema_version":"1.0"},"canonical_sha256":"771cdcef6940f107bb4e20e6dafc915625a7ed0b8fe0d80f7597903e23cf67f1","source":{"kind":"arxiv","id":"1803.07482","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.07482","created_at":"2026-05-18T00:00:43Z"},{"alias_kind":"arxiv_version","alias_value":"1803.07482v2","created_at":"2026-05-18T00:00:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.07482","created_at":"2026-05-18T00:00:43Z"},{"alias_kind":"pith_short_12","alias_value":"O4ONZ33JIDYQ","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_16","alias_value":"O4ONZ33JIDYQPO2O","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_8","alias_value":"O4ONZ33J","created_at":"2026-05-18T12:32:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:O4ONZ33JIDYQPO2OEDTNV7ERKY","target":"record","payload":{"canonical_record":{"source":{"id":"1803.07482","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-20T15:22:52Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"0bd50232f4e96163bae28d4b782f71e155eb5414d2afcdfe538434d2bd7cdc5d","abstract_canon_sha256":"a510519c486998ee74daef6b4e9456e3c920e5f5d7ed903b53a893e20a202a8a"},"schema_version":"1.0"},"canonical_sha256":"771cdcef6940f107bb4e20e6dafc915625a7ed0b8fe0d80f7597903e23cf67f1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:00:43.518467Z","signature_b64":"leUDTMDqxSubuAauY9na/pE60EkOG0gUf3PUiRXSIYoSQcXVHWBp4Wc7mxqU1Ubd0xmUuhK8wNI4D7QLn2KKAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"771cdcef6940f107bb4e20e6dafc915625a7ed0b8fe0d80f7597903e23cf67f1","last_reissued_at":"2026-05-18T00:00:43.518049Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:00:43.518049Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1803.07482","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:00:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pp+r/7qRY7Sl+iJttiKYlZsydz78OpXvDsrITo+F2fyH55VukYhj2B6kcWiPixJIm511c3K2b7jLXFwtLhkRBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T13:12:30.742022Z"},"content_sha256":"077fbdf933ccc77a6a26d9cc40796e86a7d37e44dce1ac300fb6650c0a56673a","schema_version":"1.0","event_id":"sha256:077fbdf933ccc77a6a26d9cc40796e86a7d37e44dce1ac300fb6650c0a56673a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:O4ONZ33JIDYQPO2OEDTNV7ERKY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Natural Gradient Deep Q-learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ethan Knight, Osher Lerner","submitted_at":"2018-03-20T15:22:52Z","abstract_excerpt":"We present a novel algorithm to train a deep Q-learning agent using natural-gradient techniques. We compare the original deep Q-network (DQN) algorithm to its natural-gradient counterpart, which we refer to as NGDQN, on a collection of classic control domains. Without employing target networks, NGDQN significantly outperforms DQN without target networks, and performs no worse than DQN with target networks, suggesting that NGDQN stabilizes training and can help reduce the need for additional hyperparameter tuning. We also find that NGDQN is less sensitive to hyperparameter optimization relative"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.07482","kind":"arxiv","version":2},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:00:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jOF81ru3LrT3bcP5XloyAwI6Vnyc3SXOziUR9K6/pt2NxK7ZVQAz/fhDZwgryEuFLCpFzzjgEhy+WG6mZpBbAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T13:12:30.742732Z"},"content_sha256":"2856e3782d4d39f833b47bb01fae64a6d0beec96feb691ee84b3333dc500bdad","schema_version":"1.0","event_id":"sha256:2856e3782d4d39f833b47bb01fae64a6d0beec96feb691ee84b3333dc500bdad"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/O4ONZ33JIDYQPO2OEDTNV7ERKY/bundle.json","state_url":"https://pith.science/pith/O4ONZ33JIDYQPO2OEDTNV7ERKY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/O4ONZ33JIDYQPO2OEDTNV7ERKY/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-27T13:12:30Z","links":{"resolver":"https://pith.science/pith/O4ONZ33JIDYQPO2OEDTNV7ERKY","bundle":"https://pith.science/pith/O4ONZ33JIDYQPO2OEDTNV7ERKY/bundle.json","state":"https://pith.science/pith/O4ONZ33JIDYQPO2OEDTNV7ERKY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/O4ONZ33JIDYQPO2OEDTNV7ERKY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:O4ONZ33JIDYQPO2OEDTNV7ERKY","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":"a510519c486998ee74daef6b4e9456e3c920e5f5d7ed903b53a893e20a202a8a","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-20T15:22:52Z","title_canon_sha256":"0bd50232f4e96163bae28d4b782f71e155eb5414d2afcdfe538434d2bd7cdc5d"},"schema_version":"1.0","source":{"id":"1803.07482","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.07482","created_at":"2026-05-18T00:00:43Z"},{"alias_kind":"arxiv_version","alias_value":"1803.07482v2","created_at":"2026-05-18T00:00:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.07482","created_at":"2026-05-18T00:00:43Z"},{"alias_kind":"pith_short_12","alias_value":"O4ONZ33JIDYQ","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_16","alias_value":"O4ONZ33JIDYQPO2O","created_at":"2026-05-18T12:32:40Z"},{"alias_kind":"pith_short_8","alias_value":"O4ONZ33J","created_at":"2026-05-18T12:32:40Z"}],"graph_snapshots":[{"event_id":"sha256:2856e3782d4d39f833b47bb01fae64a6d0beec96feb691ee84b3333dc500bdad","target":"graph","created_at":"2026-05-18T00:00:43Z","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":"We present a novel algorithm to train a deep Q-learning agent using natural-gradient techniques. We compare the original deep Q-network (DQN) algorithm to its natural-gradient counterpart, which we refer to as NGDQN, on a collection of classic control domains. Without employing target networks, NGDQN significantly outperforms DQN without target networks, and performs no worse than DQN with target networks, suggesting that NGDQN stabilizes training and can help reduce the need for additional hyperparameter tuning. We also find that NGDQN is less sensitive to hyperparameter optimization relative","authors_text":"Ethan Knight, Osher Lerner","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-20T15:22:52Z","title":"Natural Gradient Deep Q-learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.07482","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":"sha256:077fbdf933ccc77a6a26d9cc40796e86a7d37e44dce1ac300fb6650c0a56673a","target":"record","created_at":"2026-05-18T00:00:43Z","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":"a510519c486998ee74daef6b4e9456e3c920e5f5d7ed903b53a893e20a202a8a","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-20T15:22:52Z","title_canon_sha256":"0bd50232f4e96163bae28d4b782f71e155eb5414d2afcdfe538434d2bd7cdc5d"},"schema_version":"1.0","source":{"id":"1803.07482","kind":"arxiv","version":2}},"canonical_sha256":"771cdcef6940f107bb4e20e6dafc915625a7ed0b8fe0d80f7597903e23cf67f1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"771cdcef6940f107bb4e20e6dafc915625a7ed0b8fe0d80f7597903e23cf67f1","first_computed_at":"2026-05-18T00:00:43.518049Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:00:43.518049Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"leUDTMDqxSubuAauY9na/pE60EkOG0gUf3PUiRXSIYoSQcXVHWBp4Wc7mxqU1Ubd0xmUuhK8wNI4D7QLn2KKAg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:00:43.518467Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.07482","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:077fbdf933ccc77a6a26d9cc40796e86a7d37e44dce1ac300fb6650c0a56673a","sha256:2856e3782d4d39f833b47bb01fae64a6d0beec96feb691ee84b3333dc500bdad"],"state_sha256":"e762485065c4d9839ce2cdd590512989fd63ff4285c406016dbccd374233de1d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"90modfQ0tV49Llia/5Z2MT2AmwVeAgR/icIMeMuNVPa5UCFeNVV03Gk8mCnKi69eESmZxeJvwdMaGEemxTvXDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T13:12:30.748940Z","bundle_sha256":"f85a13c5ec2cdd5c5bc817555597455b2733193707460b06ad8648e1247edf91"}}