{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TIFMPQI64BATHPHBAVAZ4TOJ6Y","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":"0d9dc4c7a5a6c2cf2fc2c6ed664d505cad975a7da41b1bd337ba77510ac9f2f2","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-07T12:42:51Z","title_canon_sha256":"d246932f6c56925f48996e9815002ab78b54215463a3ed142fc98eb99442eac8"},"schema_version":"1.0","source":{"id":"2410.04988","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.04988","created_at":"2026-07-05T10:28:23Z"},{"alias_kind":"arxiv_version","alias_value":"2410.04988v2","created_at":"2026-07-05T10:28:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.04988","created_at":"2026-07-05T10:28:23Z"},{"alias_kind":"pith_short_12","alias_value":"TIFMPQI64BAT","created_at":"2026-07-05T10:28:23Z"},{"alias_kind":"pith_short_16","alias_value":"TIFMPQI64BATHPHB","created_at":"2026-07-05T10:28:23Z"},{"alias_kind":"pith_short_8","alias_value":"TIFMPQI6","created_at":"2026-07-05T10:28:23Z"}],"graph_snapshots":[{"event_id":"sha256:02edce458b9809dec73d9f5e2707f4ea48198c63e8defe741698254485e1220e","target":"graph","created_at":"2026-07-05T10:28:23Z","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/2410.04988/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning complex robot behavior through interactions with the environment necessitates principled exploration. Effective strategies should prioritize exploring regions of the state-action space that maximize rewards, with optimistic exploration emerging as a promising direction aligned with this idea and enabling sample-efficient reinforcement learning. However, existing methods overlook a crucial aspect: the need for optimism to be informed by a belief connecting the reward and state. To address this, we propose a practical, theoretically grounded approach to optimistic exploration based on T","authors_text":"Amanda Prorok, Carl Henrik Ek, Jasmine Bayrooti","cross_cats":["cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-07T12:42:51Z","title":"Efficient Model-Based Reinforcement Learning Through Optimistic Thompson Sampling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.04988","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":"sha256:5f6c14a3fe1e2903bb26124878dc1f72e20200e17a0d13655de0101fdc94eb5e","target":"record","created_at":"2026-07-05T10:28:23Z","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":"0d9dc4c7a5a6c2cf2fc2c6ed664d505cad975a7da41b1bd337ba77510ac9f2f2","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-07T12:42:51Z","title_canon_sha256":"d246932f6c56925f48996e9815002ab78b54215463a3ed142fc98eb99442eac8"},"schema_version":"1.0","source":{"id":"2410.04988","kind":"arxiv","version":2}},"canonical_sha256":"9a0ac7c11ee04133bce105419e4dc9f6278313e3c358550a42ee61f49b63f6aa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9a0ac7c11ee04133bce105419e4dc9f6278313e3c358550a42ee61f49b63f6aa","first_computed_at":"2026-07-05T10:28:23.739706Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:28:23.739706Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GAxPHr31+xdvxEEy9SEw7RStzesN7nSi1zcnnO1VI2TI0WlxYsMFibX7WZAL8+yKj0y2tQg4SLXQ8o2DH2L3BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:28:23.740188Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.04988","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5f6c14a3fe1e2903bb26124878dc1f72e20200e17a0d13655de0101fdc94eb5e","sha256:02edce458b9809dec73d9f5e2707f4ea48198c63e8defe741698254485e1220e"],"state_sha256":"d243b3a315f20a769ac3b06b0625e3e740f45187b44b42ee4857a4e9f75bc900"}