{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:KBRFZ5E72H4APG7H562FWEX5VS","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":"afbccc97a7c0459ebd26bf5c5d5d81270ebd5c9b3ae0345707eb3bf1b3cda022","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-06-21T20:53:19Z","title_canon_sha256":"42b1e43e96bb77fcbb4d5815076ad8d4adfce9e93277933db7adee744d3b14e3"},"schema_version":"1.0","source":{"id":"2006.11911","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.11911","created_at":"2026-07-05T03:37:38Z"},{"alias_kind":"arxiv_version","alias_value":"2006.11911v2","created_at":"2026-07-05T03:37:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.11911","created_at":"2026-07-05T03:37:38Z"},{"alias_kind":"pith_short_12","alias_value":"KBRFZ5E72H4A","created_at":"2026-07-05T03:37:38Z"},{"alias_kind":"pith_short_16","alias_value":"KBRFZ5E72H4APG7H","created_at":"2026-07-05T03:37:38Z"},{"alias_kind":"pith_short_8","alias_value":"KBRFZ5E7","created_at":"2026-07-05T03:37:38Z"}],"graph_snapshots":[{"event_id":"sha256:be9a6816c3a88f578b73b4af293ddfb6c4c6c0c8c80692596687ce5d4b5a4365","target":"graph","created_at":"2026-07-05T03:37:38Z","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/2006.11911/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The principle of optimism in the face of uncertainty is prevalent throughout sequential decision making problems such as multi-armed bandits and reinforcement learning (RL). To be successful, an optimistic RL algorithm must over-estimate the true value function (optimism) but not by so much that it is inaccurate (estimation error). In the tabular setting, many state-of-the-art methods produce the required optimism through approaches which are intractable when scaling to deep RL. We re-interpret these scalable optimistic model-based algorithms as solving a tractable noise augmented MDP. This fo","authors_text":"Aldo Pacchiano, Jack Parker-Holder, Krzysztof Choromanski, Philip J. Ball, Stephen Roberts","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-06-21T20:53:19Z","title":"Towards Tractable Optimism in Model-Based Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.11911","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":"sha256:6e4279bc7dadd3da673b2bca003ac685d1705d5e87f5bbed24e49a16292bc3fc","target":"record","created_at":"2026-07-05T03:37:38Z","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":"afbccc97a7c0459ebd26bf5c5d5d81270ebd5c9b3ae0345707eb3bf1b3cda022","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-06-21T20:53:19Z","title_canon_sha256":"42b1e43e96bb77fcbb4d5815076ad8d4adfce9e93277933db7adee744d3b14e3"},"schema_version":"1.0","source":{"id":"2006.11911","kind":"arxiv","version":2}},"canonical_sha256":"50625cf49fd1f8079be7efb45b12fdaca0ddb2ed540c189b7387e731a0e54bbf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"50625cf49fd1f8079be7efb45b12fdaca0ddb2ed540c189b7387e731a0e54bbf","first_computed_at":"2026-07-05T03:37:38.029107Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:37:38.029107Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"02ZfEnONtvybpBKEgyGPOvmnSn31/V7ToUP7Ty0u2yRK0sXfS6om8cOGVZ+58rrd/O8eAWSKjWxgwG3+VJ+KAg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:37:38.029611Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.11911","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6e4279bc7dadd3da673b2bca003ac685d1705d5e87f5bbed24e49a16292bc3fc","sha256:be9a6816c3a88f578b73b4af293ddfb6c4c6c0c8c80692596687ce5d4b5a4365"],"state_sha256":"286712c3c0c795d2fad07eb1b2c86fd65fee7bf205a0ef12e17ff33e08495ed4"}