{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:OKH7ZXWQK7AW5C7V2T7BJ6WAYD","short_pith_number":"pith:OKH7ZXWQ","schema_version":"1.0","canonical_sha256":"728ffcded057c16e8bf5d4fe14fac0c0f9a488cb38ab9804cd650fc0a57cf87a","source":{"kind":"arxiv","id":"1608.05081","version":4},"attestation_state":"computed","paper":{"title":"BBQ-Networks: Efficient Exploration in Deep Reinforcement Learning for Task-Oriented Dialogue Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Faisal Ahmed, Jianfeng Gao, Li Deng, Lihong Li, Xiujun Li, Zachary C. Lipton","submitted_at":"2016-08-17T20:00:04Z","abstract_excerpt":"We present a new algorithm that significantly improves the efficiency of exploration for deep Q-learning agents in dialogue systems. Our agents explore via Thompson sampling, drawing Monte Carlo samples from a Bayes-by-Backprop neural network. Our algorithm learns much faster than common exploration strategies such as $\\epsilon$-greedy, Boltzmann, bootstrapping, and intrinsic-reward-based ones. Additionally, we show that spiking the replay buffer with experiences from just a few successful episodes can make Q-learning feasible when it might otherwise fail."},"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":"1608.05081","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-08-17T20:00:04Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"4acf1f50a38b1c3a44c21c477c44e7cdd1363c4be16e8dbace5c71619f5e5b5b","abstract_canon_sha256":"d22b71b8bba6d3395edf5627e5ceb74c56b0d34c20ccde7bc27bd01a296bc510"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:29:31.439181Z","signature_b64":"01olYdvMFmEpm5+LDzFYSVVSnazi/YVRFAvkWHE8a7bOUpyaX9UrgmDHfNjgaTRCLZovSZrv3YmuAbT7U2SkDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"728ffcded057c16e8bf5d4fe14fac0c0f9a488cb38ab9804cd650fc0a57cf87a","last_reissued_at":"2026-05-18T00:29:31.438558Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:29:31.438558Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BBQ-Networks: Efficient Exploration in Deep Reinforcement Learning for Task-Oriented Dialogue Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Faisal Ahmed, Jianfeng Gao, Li Deng, Lihong Li, Xiujun Li, Zachary C. Lipton","submitted_at":"2016-08-17T20:00:04Z","abstract_excerpt":"We present a new algorithm that significantly improves the efficiency of exploration for deep Q-learning agents in dialogue systems. Our agents explore via Thompson sampling, drawing Monte Carlo samples from a Bayes-by-Backprop neural network. Our algorithm learns much faster than common exploration strategies such as $\\epsilon$-greedy, Boltzmann, bootstrapping, and intrinsic-reward-based ones. Additionally, we show that spiking the replay buffer with experiences from just a few successful episodes can make Q-learning feasible when it might otherwise fail."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1608.05081","kind":"arxiv","version":4},"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":"1608.05081","created_at":"2026-05-18T00:29:31.438648+00:00"},{"alias_kind":"arxiv_version","alias_value":"1608.05081v4","created_at":"2026-05-18T00:29:31.438648+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1608.05081","created_at":"2026-05-18T00:29:31.438648+00:00"},{"alias_kind":"pith_short_12","alias_value":"OKH7ZXWQK7AW","created_at":"2026-05-18T12:30:36.002864+00:00"},{"alias_kind":"pith_short_16","alias_value":"OKH7ZXWQK7AW5C7V","created_at":"2026-05-18T12:30:36.002864+00:00"},{"alias_kind":"pith_short_8","alias_value":"OKH7ZXWQ","created_at":"2026-05-18T12:30:36.002864+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/OKH7ZXWQK7AW5C7V2T7BJ6WAYD","json":"https://pith.science/pith/OKH7ZXWQK7AW5C7V2T7BJ6WAYD.json","graph_json":"https://pith.science/api/pith-number/OKH7ZXWQK7AW5C7V2T7BJ6WAYD/graph.json","events_json":"https://pith.science/api/pith-number/OKH7ZXWQK7AW5C7V2T7BJ6WAYD/events.json","paper":"https://pith.science/paper/OKH7ZXWQ"},"agent_actions":{"view_html":"https://pith.science/pith/OKH7ZXWQK7AW5C7V2T7BJ6WAYD","download_json":"https://pith.science/pith/OKH7ZXWQK7AW5C7V2T7BJ6WAYD.json","view_paper":"https://pith.science/paper/OKH7ZXWQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1608.05081&json=true","fetch_graph":"https://pith.science/api/pith-number/OKH7ZXWQK7AW5C7V2T7BJ6WAYD/graph.json","fetch_events":"https://pith.science/api/pith-number/OKH7ZXWQK7AW5C7V2T7BJ6WAYD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OKH7ZXWQK7AW5C7V2T7BJ6WAYD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OKH7ZXWQK7AW5C7V2T7BJ6WAYD/action/storage_attestation","attest_author":"https://pith.science/pith/OKH7ZXWQK7AW5C7V2T7BJ6WAYD/action/author_attestation","sign_citation":"https://pith.science/pith/OKH7ZXWQK7AW5C7V2T7BJ6WAYD/action/citation_signature","submit_replication":"https://pith.science/pith/OKH7ZXWQK7AW5C7V2T7BJ6WAYD/action/replication_record"}},"created_at":"2026-05-18T00:29:31.438648+00:00","updated_at":"2026-05-18T00:29:31.438648+00:00"}