{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:3ZHSQ2I6R3T37ETVTNX6OJSO3M","short_pith_number":"pith:3ZHSQ2I6","schema_version":"1.0","canonical_sha256":"de4f28691e8ee7bf92759b6fe7264edb18f4b7d5c57892eb790cd3fc3dffc7ae","source":{"kind":"arxiv","id":"1511.06581","version":3},"attestation_state":"computed","paper":{"title":"Dueling Network Architectures for Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hado van Hasselt, Marc Lanctot, Matteo Hessel, Nando de Freitas, Tom Schaul, Ziyu Wang","submitted_at":"2015-11-20T13:07:54Z","abstract_excerpt":"In recent years there have been many successes of using deep representations in reinforcement learning. Still, many of these applications use conventional architectures, such as convolutional networks, LSTMs, or auto-encoders. In this paper, we present a new neural network architecture for model-free reinforcement learning. Our dueling network represents two separate estimators: one for the state value function and one for the state-dependent action advantage function. The main benefit of this factoring is to generalize learning across actions without imposing any change to the underlying rein"},"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":"1511.06581","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-20T13:07:54Z","cross_cats_sorted":[],"title_canon_sha256":"ace1e6d10a3703390b2d84cd1eacb674f97ae5bf67b657945645a79cc2cb1fbb","abstract_canon_sha256":"c9ce4af50cbca545fef340d09a714e990e6197db0d28bf47bf31436f03186e5a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:17:46.933996Z","signature_b64":"NZaNw1N+lpK/yw3v8oLMP+8KL8AsQh6CB1XcLgbSUWgP+hpxDYpQdju3V6G51lUeDsYU4o0E2H2ifRsVVDESCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de4f28691e8ee7bf92759b6fe7264edb18f4b7d5c57892eb790cd3fc3dffc7ae","last_reissued_at":"2026-05-18T01:17:46.933061Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:17:46.933061Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dueling Network Architectures for Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hado van Hasselt, Marc Lanctot, Matteo Hessel, Nando de Freitas, Tom Schaul, Ziyu Wang","submitted_at":"2015-11-20T13:07:54Z","abstract_excerpt":"In recent years there have been many successes of using deep representations in reinforcement learning. Still, many of these applications use conventional architectures, such as convolutional networks, LSTMs, or auto-encoders. In this paper, we present a new neural network architecture for model-free reinforcement learning. Our dueling network represents two separate estimators: one for the state value function and one for the state-dependent action advantage function. The main benefit of this factoring is to generalize learning across actions without imposing any change to the underlying rein"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.06581","kind":"arxiv","version":3},"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":"1511.06581","created_at":"2026-05-18T01:17:46.933188+00:00"},{"alias_kind":"arxiv_version","alias_value":"1511.06581v3","created_at":"2026-05-18T01:17:46.933188+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.06581","created_at":"2026-05-18T01:17:46.933188+00:00"},{"alias_kind":"pith_short_12","alias_value":"3ZHSQ2I6R3T3","created_at":"2026-05-18T12:29:02.477457+00:00"},{"alias_kind":"pith_short_16","alias_value":"3ZHSQ2I6R3T37ETV","created_at":"2026-05-18T12:29:02.477457+00:00"},{"alias_kind":"pith_short_8","alias_value":"3ZHSQ2I6","created_at":"2026-05-18T12:29:02.477457+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/3ZHSQ2I6R3T37ETVTNX6OJSO3M","json":"https://pith.science/pith/3ZHSQ2I6R3T37ETVTNX6OJSO3M.json","graph_json":"https://pith.science/api/pith-number/3ZHSQ2I6R3T37ETVTNX6OJSO3M/graph.json","events_json":"https://pith.science/api/pith-number/3ZHSQ2I6R3T37ETVTNX6OJSO3M/events.json","paper":"https://pith.science/paper/3ZHSQ2I6"},"agent_actions":{"view_html":"https://pith.science/pith/3ZHSQ2I6R3T37ETVTNX6OJSO3M","download_json":"https://pith.science/pith/3ZHSQ2I6R3T37ETVTNX6OJSO3M.json","view_paper":"https://pith.science/paper/3ZHSQ2I6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1511.06581&json=true","fetch_graph":"https://pith.science/api/pith-number/3ZHSQ2I6R3T37ETVTNX6OJSO3M/graph.json","fetch_events":"https://pith.science/api/pith-number/3ZHSQ2I6R3T37ETVTNX6OJSO3M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3ZHSQ2I6R3T37ETVTNX6OJSO3M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3ZHSQ2I6R3T37ETVTNX6OJSO3M/action/storage_attestation","attest_author":"https://pith.science/pith/3ZHSQ2I6R3T37ETVTNX6OJSO3M/action/author_attestation","sign_citation":"https://pith.science/pith/3ZHSQ2I6R3T37ETVTNX6OJSO3M/action/citation_signature","submit_replication":"https://pith.science/pith/3ZHSQ2I6R3T37ETVTNX6OJSO3M/action/replication_record"}},"created_at":"2026-05-18T01:17:46.933188+00:00","updated_at":"2026-05-18T01:17:46.933188+00:00"}