{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:BKSHVCNZO7WRX672PTFAZXKVFJ","short_pith_number":"pith:BKSHVCNZ","canonical_record":{"source":{"id":"1810.00368","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-09-30T12:52:31Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"49dc848882b242e4e49cf5318d224828aa23e2849105203c775100ceefcec0bf","abstract_canon_sha256":"3d8c3130b83b5615aa916cb4606f7b71d27b4f0c2a0cdf903f6daf472e01a45f"},"schema_version":"1.0"},"canonical_sha256":"0aa47a89b977ed1bfbfa7cca0cdd552a7d929649042af73fa7720567d040b666","source":{"kind":"arxiv","id":"1810.00368","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.00368","created_at":"2026-05-18T00:03:40Z"},{"alias_kind":"arxiv_version","alias_value":"1810.00368v2","created_at":"2026-05-18T00:03:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.00368","created_at":"2026-05-18T00:03:40Z"},{"alias_kind":"pith_short_12","alias_value":"BKSHVCNZO7WR","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_16","alias_value":"BKSHVCNZO7WRX672","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_8","alias_value":"BKSHVCNZ","created_at":"2026-05-18T12:32:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:BKSHVCNZO7WRX672PTFAZXKVFJ","target":"record","payload":{"canonical_record":{"source":{"id":"1810.00368","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-09-30T12:52:31Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"49dc848882b242e4e49cf5318d224828aa23e2849105203c775100ceefcec0bf","abstract_canon_sha256":"3d8c3130b83b5615aa916cb4606f7b71d27b4f0c2a0cdf903f6daf472e01a45f"},"schema_version":"1.0"},"canonical_sha256":"0aa47a89b977ed1bfbfa7cca0cdd552a7d929649042af73fa7720567d040b666","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:03:40.951155Z","signature_b64":"hntAQj50jlRSzlAa41SDQd7jj/mtYhZ3MNeNiCp/c/9BzfXIGqwY/rEiKiuy6vmjjwrAYAYLMw5I9G5cMYk4Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0aa47a89b977ed1bfbfa7cca0cdd552a7d929649042af73fa7720567d040b666","last_reissued_at":"2026-05-18T00:03:40.950684Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:03:40.950684Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.00368","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":"2026-05-18T00:03:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q0jwVfU1rwtU3Gi4+z2OmcorAlqwluxgyFXSHFqsMdvlcUUtiHiKLwJc4ArGIxQPyJg1N4cfafGvbTclUP6iAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-23T03:24:03.738645Z"},"content_sha256":"230140816829633a1045607a394e1f696b87d72d2ae7c15f0fb6e32ba80b1c5a","schema_version":"1.0","event_id":"sha256:230140816829633a1045607a394e1f696b87d72d2ae7c15f0fb6e32ba80b1c5a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:BKSHVCNZO7WRX672PTFAZXKVFJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Quality-Value (DQV) Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Gilles Louppe, Marco A. Wiering, Matthia Sabatelli, Pierre Geurts","submitted_at":"2018-09-30T12:52:31Z","abstract_excerpt":"We introduce a novel Deep Reinforcement Learning (DRL) algorithm called Deep Quality-Value (DQV) Learning. DQV uses temporal-difference learning to train a Value neural network and uses this network for training a second Quality-value network that learns to estimate state-action values. We first test DQV's update rules with Multilayer Perceptrons as function approximators on two classic RL problems, and then extend DQV with the use of Deep Convolutional Neural Networks, `Experience Replay' and `Target Neural Networks' for tackling four games of the Atari Arcade Learning environment. Our result"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.00368","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":"2026-05-18T00:03:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VQrFImDeV3x7uSiIR6HpjdfoGQ9Zno8Cp1NSL64G/9Z9FzwucebtAjTOAeNoDmhd1ahqC9iJWSab7rAQbqUMCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-23T03:24:03.738992Z"},"content_sha256":"0781b21188662419d0cd5fa7186d174448856001935d406d2a2212c0d047c68b","schema_version":"1.0","event_id":"sha256:0781b21188662419d0cd5fa7186d174448856001935d406d2a2212c0d047c68b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BKSHVCNZO7WRX672PTFAZXKVFJ/bundle.json","state_url":"https://pith.science/pith/BKSHVCNZO7WRX672PTFAZXKVFJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BKSHVCNZO7WRX672PTFAZXKVFJ/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":"2026-06-23T03:24:03Z","links":{"resolver":"https://pith.science/pith/BKSHVCNZO7WRX672PTFAZXKVFJ","bundle":"https://pith.science/pith/BKSHVCNZO7WRX672PTFAZXKVFJ/bundle.json","state":"https://pith.science/pith/BKSHVCNZO7WRX672PTFAZXKVFJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BKSHVCNZO7WRX672PTFAZXKVFJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:BKSHVCNZO7WRX672PTFAZXKVFJ","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":"3d8c3130b83b5615aa916cb4606f7b71d27b4f0c2a0cdf903f6daf472e01a45f","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-09-30T12:52:31Z","title_canon_sha256":"49dc848882b242e4e49cf5318d224828aa23e2849105203c775100ceefcec0bf"},"schema_version":"1.0","source":{"id":"1810.00368","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.00368","created_at":"2026-05-18T00:03:40Z"},{"alias_kind":"arxiv_version","alias_value":"1810.00368v2","created_at":"2026-05-18T00:03:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.00368","created_at":"2026-05-18T00:03:40Z"},{"alias_kind":"pith_short_12","alias_value":"BKSHVCNZO7WR","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_16","alias_value":"BKSHVCNZO7WRX672","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_8","alias_value":"BKSHVCNZ","created_at":"2026-05-18T12:32:16Z"}],"graph_snapshots":[{"event_id":"sha256:0781b21188662419d0cd5fa7186d174448856001935d406d2a2212c0d047c68b","target":"graph","created_at":"2026-05-18T00:03:40Z","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 introduce a novel Deep Reinforcement Learning (DRL) algorithm called Deep Quality-Value (DQV) Learning. DQV uses temporal-difference learning to train a Value neural network and uses this network for training a second Quality-value network that learns to estimate state-action values. We first test DQV's update rules with Multilayer Perceptrons as function approximators on two classic RL problems, and then extend DQV with the use of Deep Convolutional Neural Networks, `Experience Replay' and `Target Neural Networks' for tackling four games of the Atari Arcade Learning environment. Our result","authors_text":"Gilles Louppe, Marco A. Wiering, Matthia Sabatelli, Pierre Geurts","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-09-30T12:52:31Z","title":"Deep Quality-Value (DQV) Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.00368","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":"sha256:230140816829633a1045607a394e1f696b87d72d2ae7c15f0fb6e32ba80b1c5a","target":"record","created_at":"2026-05-18T00:03:40Z","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":"3d8c3130b83b5615aa916cb4606f7b71d27b4f0c2a0cdf903f6daf472e01a45f","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-09-30T12:52:31Z","title_canon_sha256":"49dc848882b242e4e49cf5318d224828aa23e2849105203c775100ceefcec0bf"},"schema_version":"1.0","source":{"id":"1810.00368","kind":"arxiv","version":2}},"canonical_sha256":"0aa47a89b977ed1bfbfa7cca0cdd552a7d929649042af73fa7720567d040b666","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0aa47a89b977ed1bfbfa7cca0cdd552a7d929649042af73fa7720567d040b666","first_computed_at":"2026-05-18T00:03:40.950684Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:03:40.950684Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hntAQj50jlRSzlAa41SDQd7jj/mtYhZ3MNeNiCp/c/9BzfXIGqwY/rEiKiuy6vmjjwrAYAYLMw5I9G5cMYk4Cw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:03:40.951155Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.00368","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:230140816829633a1045607a394e1f696b87d72d2ae7c15f0fb6e32ba80b1c5a","sha256:0781b21188662419d0cd5fa7186d174448856001935d406d2a2212c0d047c68b"],"state_sha256":"28bb8724492de815799cf42260387ea16eeabc8ac0f12fd0ac8f1113f817187b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yzb2UB6IFCkg6YDOGrjYMsM+UTxYnAGe21CLXsaPelHBDVCW5V9Z7G9Al3FKwWX6lFLBz0zwt4ag4Ic73bUbAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-23T03:24:03.741022Z","bundle_sha256":"8667aefe7314cd8c846bed49262b620e3445c6c88344655fd70faf0a77e1f7d2"}}