{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:JL5OSIW4MN2W7HIMCV4S24HIFN","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"473d338aa04768f1de09cc85f45d00979a4b784ee8170b071a45b672874286eb","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-06-05T19:01:26Z","title_canon_sha256":"1a2e20bb1ccc770f804463f10aaae6560582079dfc580a5b3c4b9b5b1ad21348"},"schema_version":"1.0","source":{"id":"1706.01502","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.01502","created_at":"2026-05-18T00:31:02Z"},{"alias_kind":"arxiv_version","alias_value":"1706.01502v3","created_at":"2026-05-18T00:31:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.01502","created_at":"2026-05-18T00:31:02Z"},{"alias_kind":"pith_short_12","alias_value":"JL5OSIW4MN2W","created_at":"2026-05-18T12:31:24Z"},{"alias_kind":"pith_short_16","alias_value":"JL5OSIW4MN2W7HIM","created_at":"2026-05-18T12:31:24Z"},{"alias_kind":"pith_short_8","alias_value":"JL5OSIW4","created_at":"2026-05-18T12:31:24Z"}],"graph_snapshots":[{"event_id":"sha256:2516f617b8c6f3f96dcd94d470d42d4e2015b6bbd4576264a82002c97d35e489","target":"graph","created_at":"2026-05-18T00:31:02Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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.","authors_text":"John Schulman, Pieter Abbeel, Richard Y. Chen, Szymon Sidor","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-06-05T19:01:26Z","title":"UCB Exploration via Q-Ensembles"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.01502","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5b7f86a307f7ede595024e15de78bf0d8f70b9a25a5154d27b0aa13457da43d4","target":"record","created_at":"2026-05-18T00:31:02Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"473d338aa04768f1de09cc85f45d00979a4b784ee8170b071a45b672874286eb","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-06-05T19:01:26Z","title_canon_sha256":"1a2e20bb1ccc770f804463f10aaae6560582079dfc580a5b3c4b9b5b1ad21348"},"schema_version":"1.0","source":{"id":"1706.01502","kind":"arxiv","version":3}},"canonical_sha256":"4afae922dc63756f9d0c15792d70e82b5e1a904118aeb2a46669e19fe4b81860","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4afae922dc63756f9d0c15792d70e82b5e1a904118aeb2a46669e19fe4b81860","first_computed_at":"2026-05-18T00:31:02.765554Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:31:02.765554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"crIak6edlj0QEM5pYcG3kaiOuGSAZXcvao8wPBfZnZVuybhrGu2VosjIiZCEKeU9Sg47a+Euxhz/ABabtc9sDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:31:02.766112Z","signed_message":"canonical_sha256_bytes"},"source_id":"1706.01502","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5b7f86a307f7ede595024e15de78bf0d8f70b9a25a5154d27b0aa13457da43d4","sha256:2516f617b8c6f3f96dcd94d470d42d4e2015b6bbd4576264a82002c97d35e489"],"state_sha256":"bf09f8450204dfee0e16dad5ea6fc5e52b4fd026665b006b617e87ebc94b42ac"}