{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:QV4TYLZAOAWCTTIO6IZFMEOQXT","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":"61e4fa2d64deef245fb216ccb4d55b5e38db7880e3690fc700f0f1d05165c2e5","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-17T22:29:23Z","title_canon_sha256":"840772fe6da8509beadc616682bc486e1fd2c971fd0b35359423e5db8ed041f6"},"schema_version":"1.0","source":{"id":"2002.07282","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.07282","created_at":"2026-07-05T02:17:20Z"},{"alias_kind":"arxiv_version","alias_value":"2002.07282v2","created_at":"2026-07-05T02:17:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.07282","created_at":"2026-07-05T02:17:20Z"},{"alias_kind":"pith_short_12","alias_value":"QV4TYLZAOAWC","created_at":"2026-07-05T02:17:20Z"},{"alias_kind":"pith_short_16","alias_value":"QV4TYLZAOAWCTTIO","created_at":"2026-07-05T02:17:20Z"},{"alias_kind":"pith_short_8","alias_value":"QV4TYLZA","created_at":"2026-07-05T02:17:20Z"}],"graph_snapshots":[{"event_id":"sha256:3b1bf392ac4508f95277be415ea865e6a79d0fcd1a118e87d9ccb920eb92b250","target":"graph","created_at":"2026-07-05T02:17:20Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2002.07282/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Algorithms that tackle deep exploration -- an important challenge in reinforcement learning -- have relied on epistemic uncertainty representation through ensembles or other hypermodels, exploration bonuses, or visitation count distributions. An open question is whether deep exploration can be achieved by an incremental reinforcement learning algorithm that tracks a single point estimate, without additional complexity required to account for epistemic uncertainty. We answer this question in the affirmative. In particular, we develop Langevin DQN, a variation of DQN that differs only in perturb","authors_text":"Benjamin Van Roy, Vikranth Dwaracherla","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-17T22:29:23Z","title":"Langevin DQN"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.07282","kind":"arxiv","version":2},"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":"sha256:522e4cda0de2231637b45222c139979770165fdd0842c10bbc2bac4b8f194f2c","target":"record","created_at":"2026-07-05T02:17:20Z","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":"61e4fa2d64deef245fb216ccb4d55b5e38db7880e3690fc700f0f1d05165c2e5","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-17T22:29:23Z","title_canon_sha256":"840772fe6da8509beadc616682bc486e1fd2c971fd0b35359423e5db8ed041f6"},"schema_version":"1.0","source":{"id":"2002.07282","kind":"arxiv","version":2}},"canonical_sha256":"85793c2f20702c29cd0ef2325611d0bcf1b714f264e9473bb53a5c3bd2507b8c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"85793c2f20702c29cd0ef2325611d0bcf1b714f264e9473bb53a5c3bd2507b8c","first_computed_at":"2026-07-05T02:17:20.278972Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:17:20.278972Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Qs5j3MOJWMcfjN8bxStfnsUjzchGq0h/2sYe6LwWd70qFxHOjGh0KfnD+QLSJkAm3D55cbFMbg5APnrX/uYwCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:17:20.279437Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.07282","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:522e4cda0de2231637b45222c139979770165fdd0842c10bbc2bac4b8f194f2c","sha256:3b1bf392ac4508f95277be415ea865e6a79d0fcd1a118e87d9ccb920eb92b250"],"state_sha256":"7832362017a41c6cefb39711d8b26a613d12f87949581986ed6383f723ed90ff"}