{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:JL5OSIW4MN2W7HIMCV4S24HIFN","short_pith_number":"pith:JL5OSIW4","schema_version":"1.0","canonical_sha256":"4afae922dc63756f9d0c15792d70e82b5e1a904118aeb2a46669e19fe4b81860","source":{"kind":"arxiv","id":"1706.01502","version":3},"attestation_state":"computed","paper":{"title":"UCB Exploration via Q-Ensembles","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"John Schulman, Pieter Abbeel, Richard Y. Chen, Szymon Sidor","submitted_at":"2017-06-05T19:01:26Z","abstract_excerpt":"We show how an ensemble of $Q^*$-functions can be leveraged for more effective exploration in deep reinforcement learning. We build on well established algorithms from the bandit setting, and adapt them to the $Q$-learning setting. We propose an exploration strategy based on upper-confidence bounds (UCB). Our experiments show significant gains on the Atari benchmark."},"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":"1706.01502","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-06-05T19:01:26Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"1a2e20bb1ccc770f804463f10aaae6560582079dfc580a5b3c4b9b5b1ad21348","abstract_canon_sha256":"473d338aa04768f1de09cc85f45d00979a4b784ee8170b071a45b672874286eb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:31:02.766112Z","signature_b64":"crIak6edlj0QEM5pYcG3kaiOuGSAZXcvao8wPBfZnZVuybhrGu2VosjIiZCEKeU9Sg47a+Euxhz/ABabtc9sDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4afae922dc63756f9d0c15792d70e82b5e1a904118aeb2a46669e19fe4b81860","last_reissued_at":"2026-05-18T00:31:02.765554Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:31:02.765554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UCB Exploration via Q-Ensembles","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"John Schulman, Pieter Abbeel, Richard Y. Chen, Szymon Sidor","submitted_at":"2017-06-05T19:01:26Z","abstract_excerpt":"We show how an ensemble of $Q^*$-functions can be leveraged for more effective exploration in deep reinforcement learning. We build on well established algorithms from the bandit setting, and adapt them to the $Q$-learning setting. We propose an exploration strategy based on upper-confidence bounds (UCB). Our experiments show significant gains on the Atari benchmark."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.01502","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":"1706.01502","created_at":"2026-05-18T00:31:02.765653+00:00"},{"alias_kind":"arxiv_version","alias_value":"1706.01502v3","created_at":"2026-05-18T00:31:02.765653+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.01502","created_at":"2026-05-18T00:31:02.765653+00:00"},{"alias_kind":"pith_short_12","alias_value":"JL5OSIW4MN2W","created_at":"2026-05-18T12:31:24.725408+00:00"},{"alias_kind":"pith_short_16","alias_value":"JL5OSIW4MN2W7HIM","created_at":"2026-05-18T12:31:24.725408+00:00"},{"alias_kind":"pith_short_8","alias_value":"JL5OSIW4","created_at":"2026-05-18T12:31:24.725408+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"2602.06239","citing_title":"Provably avoiding over-optimization in Direct Preference Optimization without knowing the data distribution","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2507.23501","citing_title":"Adaptive Ensemble Aggregation for Actor-Critics","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2512.17091","citing_title":"Learning to Plan, Planning to Learn: Adaptive Hierarchical RL-MPC for Sample-Efficient Decision Making","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2602.06239","citing_title":"Provably avoiding over-optimization in Direct Preference Optimization without knowing the data distribution","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2604.18143","citing_title":"Distributional Off-Policy Evaluation with Deep Quantile Process Regression","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JL5OSIW4MN2W7HIMCV4S24HIFN","json":"https://pith.science/pith/JL5OSIW4MN2W7HIMCV4S24HIFN.json","graph_json":"https://pith.science/api/pith-number/JL5OSIW4MN2W7HIMCV4S24HIFN/graph.json","events_json":"https://pith.science/api/pith-number/JL5OSIW4MN2W7HIMCV4S24HIFN/events.json","paper":"https://pith.science/paper/JL5OSIW4"},"agent_actions":{"view_html":"https://pith.science/pith/JL5OSIW4MN2W7HIMCV4S24HIFN","download_json":"https://pith.science/pith/JL5OSIW4MN2W7HIMCV4S24HIFN.json","view_paper":"https://pith.science/paper/JL5OSIW4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1706.01502&json=true","fetch_graph":"https://pith.science/api/pith-number/JL5OSIW4MN2W7HIMCV4S24HIFN/graph.json","fetch_events":"https://pith.science/api/pith-number/JL5OSIW4MN2W7HIMCV4S24HIFN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JL5OSIW4MN2W7HIMCV4S24HIFN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JL5OSIW4MN2W7HIMCV4S24HIFN/action/storage_attestation","attest_author":"https://pith.science/pith/JL5OSIW4MN2W7HIMCV4S24HIFN/action/author_attestation","sign_citation":"https://pith.science/pith/JL5OSIW4MN2W7HIMCV4S24HIFN/action/citation_signature","submit_replication":"https://pith.science/pith/JL5OSIW4MN2W7HIMCV4S24HIFN/action/replication_record"}},"created_at":"2026-05-18T00:31:02.765653+00:00","updated_at":"2026-05-18T00:31:02.765653+00:00"}