{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:ZDRB6FZB2E3BSWE7MN2UTHLJ4O","short_pith_number":"pith:ZDRB6FZB","schema_version":"1.0","canonical_sha256":"c8e21f1721d13619589f6375499d69e39a29fc76abe7d3c86e92f55e1713cde1","source":{"kind":"arxiv","id":"1806.03335","version":2},"attestation_state":"computed","paper":{"title":"Randomized Prior Functions for Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Albin Cassirer, Ian Osband, John Aslanides","submitted_at":"2018-06-08T19:47:54Z","abstract_excerpt":"Dealing with uncertainty is essential for efficient reinforcement learning. There is a growing literature on uncertainty estimation for deep learning from fixed datasets, but many of the most popular approaches are poorly-suited to sequential decision problems. Other methods, such as bootstrap sampling, have no mechanism for uncertainty that does not come from the observed data. We highlight why this can be a crucial shortcoming and propose a simple remedy through addition of a randomized untrainable `prior' network to each ensemble member. We prove that this approach is efficient with linear "},"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":"1806.03335","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-06-08T19:47:54Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"32c13bdf77fed701f579f6c3cbe8127a9d57e9cc82783a797eda8bb45dac6ad9","abstract_canon_sha256":"359220c2734c6f5de5002e82e7b30b61383fd2424a131a8ffe038ce41ad5c38b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:00:39.519828Z","signature_b64":"4fJY5Wwnxfw/vLxLLuPdhHOOix87eEmXAxJ8XUCQLu8pvs+ZLBPa4DOgb5+1kKjtcPrh1CyO22gv3j0pjTNNAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8e21f1721d13619589f6375499d69e39a29fc76abe7d3c86e92f55e1713cde1","last_reissued_at":"2026-05-18T00:00:39.519360Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:00:39.519360Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Randomized Prior Functions for Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Albin Cassirer, Ian Osband, John Aslanides","submitted_at":"2018-06-08T19:47:54Z","abstract_excerpt":"Dealing with uncertainty is essential for efficient reinforcement learning. There is a growing literature on uncertainty estimation for deep learning from fixed datasets, but many of the most popular approaches are poorly-suited to sequential decision problems. Other methods, such as bootstrap sampling, have no mechanism for uncertainty that does not come from the observed data. We highlight why this can be a crucial shortcoming and propose a simple remedy through addition of a randomized untrainable `prior' network to each ensemble member. We prove that this approach is efficient with linear "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.03335","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1806.03335","created_at":"2026-05-18T00:00:39.519433+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.03335v2","created_at":"2026-05-18T00:00:39.519433+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.03335","created_at":"2026-05-18T00:00:39.519433+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZDRB6FZB2E3B","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZDRB6FZB2E3BSWE7","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZDRB6FZB","created_at":"2026-05-18T12:33:07.085635+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/ZDRB6FZB2E3BSWE7MN2UTHLJ4O","json":"https://pith.science/pith/ZDRB6FZB2E3BSWE7MN2UTHLJ4O.json","graph_json":"https://pith.science/api/pith-number/ZDRB6FZB2E3BSWE7MN2UTHLJ4O/graph.json","events_json":"https://pith.science/api/pith-number/ZDRB6FZB2E3BSWE7MN2UTHLJ4O/events.json","paper":"https://pith.science/paper/ZDRB6FZB"},"agent_actions":{"view_html":"https://pith.science/pith/ZDRB6FZB2E3BSWE7MN2UTHLJ4O","download_json":"https://pith.science/pith/ZDRB6FZB2E3BSWE7MN2UTHLJ4O.json","view_paper":"https://pith.science/paper/ZDRB6FZB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.03335&json=true","fetch_graph":"https://pith.science/api/pith-number/ZDRB6FZB2E3BSWE7MN2UTHLJ4O/graph.json","fetch_events":"https://pith.science/api/pith-number/ZDRB6FZB2E3BSWE7MN2UTHLJ4O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZDRB6FZB2E3BSWE7MN2UTHLJ4O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZDRB6FZB2E3BSWE7MN2UTHLJ4O/action/storage_attestation","attest_author":"https://pith.science/pith/ZDRB6FZB2E3BSWE7MN2UTHLJ4O/action/author_attestation","sign_citation":"https://pith.science/pith/ZDRB6FZB2E3BSWE7MN2UTHLJ4O/action/citation_signature","submit_replication":"https://pith.science/pith/ZDRB6FZB2E3BSWE7MN2UTHLJ4O/action/replication_record"}},"created_at":"2026-05-18T00:00:39.519433+00:00","updated_at":"2026-05-18T00:00:39.519433+00:00"}