{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:VESOUDSKJGOJTEC7WYFF44X7E5","short_pith_number":"pith:VESOUDSK","schema_version":"1.0","canonical_sha256":"a924ea0e4a499c99905fb60a5e72ff2776e204ac72c034301b3f06262ac5ccb3","source":{"kind":"arxiv","id":"1602.04621","version":3},"attestation_state":"computed","paper":{"title":"Deep Exploration via Bootstrapped DQN","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SY","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Pritzel, Benjamin Van Roy, Charles Blundell, Ian Osband","submitted_at":"2016-02-15T10:54:20Z","abstract_excerpt":"Efficient exploration in complex environments remains a major challenge for reinforcement learning. We propose bootstrapped DQN, a simple algorithm that explores in a computationally and statistically efficient manner through use of randomized value functions. Unlike dithering strategies such as epsilon-greedy exploration, bootstrapped DQN carries out temporally-extended (or deep) exploration; this can lead to exponentially faster learning. We demonstrate these benefits in complex stochastic MDPs and in the large-scale Arcade Learning Environment. Bootstrapped DQN substantially improves learni"},"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":"1602.04621","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-02-15T10:54:20Z","cross_cats_sorted":["cs.AI","cs.SY","stat.ML"],"title_canon_sha256":"621d13267d877a030382100a278ca40a80f396f2ddf3576392f276475713c854","abstract_canon_sha256":"df94824d02f69d9e86a990b6f5e14fc131447de6acd246eda001761626903cf8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:11:35.065245Z","signature_b64":"wSZDfktLyJlv4RBRQ/uM8ASn/err/g0Roi6h7v0pq/tA8aKCGDWpwRph8P99xeFP58YcKdfGQ+WYPFrBrRXJBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a924ea0e4a499c99905fb60a5e72ff2776e204ac72c034301b3f06262ac5ccb3","last_reissued_at":"2026-05-18T01:11:35.064825Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:11:35.064825Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Exploration via Bootstrapped DQN","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SY","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Pritzel, Benjamin Van Roy, Charles Blundell, Ian Osband","submitted_at":"2016-02-15T10:54:20Z","abstract_excerpt":"Efficient exploration in complex environments remains a major challenge for reinforcement learning. We propose bootstrapped DQN, a simple algorithm that explores in a computationally and statistically efficient manner through use of randomized value functions. Unlike dithering strategies such as epsilon-greedy exploration, bootstrapped DQN carries out temporally-extended (or deep) exploration; this can lead to exponentially faster learning. We demonstrate these benefits in complex stochastic MDPs and in the large-scale Arcade Learning Environment. Bootstrapped DQN substantially improves learni"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1602.04621","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":"1602.04621","created_at":"2026-05-18T01:11:35.064894+00:00"},{"alias_kind":"arxiv_version","alias_value":"1602.04621v3","created_at":"2026-05-18T01:11:35.064894+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.04621","created_at":"2026-05-18T01:11:35.064894+00:00"},{"alias_kind":"pith_short_12","alias_value":"VESOUDSKJGOJ","created_at":"2026-05-18T12:30:48.956258+00:00"},{"alias_kind":"pith_short_16","alias_value":"VESOUDSKJGOJTEC7","created_at":"2026-05-18T12:30:48.956258+00:00"},{"alias_kind":"pith_short_8","alias_value":"VESOUDSK","created_at":"2026-05-18T12:30:48.956258+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2006.12024","citing_title":"Bayesian Neural Networks: An Introduction and Survey","ref_index":119,"is_internal_anchor":true},{"citing_arxiv_id":"1606.06565","citing_title":"Concrete Problems in AI Safety","ref_index":115,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VESOUDSKJGOJTEC7WYFF44X7E5","json":"https://pith.science/pith/VESOUDSKJGOJTEC7WYFF44X7E5.json","graph_json":"https://pith.science/api/pith-number/VESOUDSKJGOJTEC7WYFF44X7E5/graph.json","events_json":"https://pith.science/api/pith-number/VESOUDSKJGOJTEC7WYFF44X7E5/events.json","paper":"https://pith.science/paper/VESOUDSK"},"agent_actions":{"view_html":"https://pith.science/pith/VESOUDSKJGOJTEC7WYFF44X7E5","download_json":"https://pith.science/pith/VESOUDSKJGOJTEC7WYFF44X7E5.json","view_paper":"https://pith.science/paper/VESOUDSK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1602.04621&json=true","fetch_graph":"https://pith.science/api/pith-number/VESOUDSKJGOJTEC7WYFF44X7E5/graph.json","fetch_events":"https://pith.science/api/pith-number/VESOUDSKJGOJTEC7WYFF44X7E5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VESOUDSKJGOJTEC7WYFF44X7E5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VESOUDSKJGOJTEC7WYFF44X7E5/action/storage_attestation","attest_author":"https://pith.science/pith/VESOUDSKJGOJTEC7WYFF44X7E5/action/author_attestation","sign_citation":"https://pith.science/pith/VESOUDSKJGOJTEC7WYFF44X7E5/action/citation_signature","submit_replication":"https://pith.science/pith/VESOUDSKJGOJTEC7WYFF44X7E5/action/replication_record"}},"created_at":"2026-05-18T01:11:35.064894+00:00","updated_at":"2026-05-18T01:11:35.064894+00:00"}