{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VVYNVDQG3PXDHCWEPVDJTICU4E","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":"ca644bc79e0e6ada0f695f272ac81d2eafb88bbbcdaf8ad8fb405ed240c81494","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-06T13:58:41Z","title_canon_sha256":"0cba5465a9fc23378b5a6c3f6fd66472316d342ee794b2dcab4bcf59e5ae4539"},"schema_version":"1.0","source":{"id":"2406.04088","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.04088","created_at":"2026-07-05T10:01:33Z"},{"alias_kind":"arxiv_version","alias_value":"2406.04088v3","created_at":"2026-07-05T10:01:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04088","created_at":"2026-07-05T10:01:33Z"},{"alias_kind":"pith_short_12","alias_value":"VVYNVDQG3PXD","created_at":"2026-07-05T10:01:33Z"},{"alias_kind":"pith_short_16","alias_value":"VVYNVDQG3PXDHCWE","created_at":"2026-07-05T10:01:33Z"},{"alias_kind":"pith_short_8","alias_value":"VVYNVDQG","created_at":"2026-07-05T10:01:33Z"}],"graph_snapshots":[{"event_id":"sha256:3371ba9e8cd798d1b6675ac31cf5e646b02bc56f8332d4e2d014cc9417b55438","target":"graph","created_at":"2026-07-05T10:01:33Z","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/2406.04088/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current approaches to model-based offline reinforcement learning often incorporate uncertainty-based reward penalization to address the distributional shift problem. These approaches, commonly known as pessimistic value iteration, use Monte Carlo sampling to estimate the Bellman target to perform temporal difference-based policy evaluation. We find out that the randomness caused by this sampling step significantly delays convergence. We present a theoretical result demonstrating the strong dependency of suboptimality on the number of Monte Carlo samples taken per Bellman target calculation. Ou","authors_text":"Abdullah Akg\\\"ul, Manuel Hau{\\ss}mann, Melih Kandemir","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-06T13:58:41Z","title":"Deterministic Uncertainty Propagation for Improved Model-Based Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04088","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":"sha256:44181d85382a048fd7859f85034a03d4d01e9a842629eb1aca4748757828e33a","target":"record","created_at":"2026-07-05T10:01:33Z","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":"ca644bc79e0e6ada0f695f272ac81d2eafb88bbbcdaf8ad8fb405ed240c81494","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-06T13:58:41Z","title_canon_sha256":"0cba5465a9fc23378b5a6c3f6fd66472316d342ee794b2dcab4bcf59e5ae4539"},"schema_version":"1.0","source":{"id":"2406.04088","kind":"arxiv","version":3}},"canonical_sha256":"ad70da8e06dbee338ac47d4699a054e13f6fa94158cdf8d835dcb23d587a47e1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ad70da8e06dbee338ac47d4699a054e13f6fa94158cdf8d835dcb23d587a47e1","first_computed_at":"2026-07-05T10:01:33.825723Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:01:33.825723Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"z5GqC+Aa7o1lW2mCB8f1z8noSJXlz6ZQOnlGatK0cS8goGQC6t7iXsNlHPnz8k+ZIzHkMje5A9JgEcBGOxjwDg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:01:33.826253Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.04088","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:44181d85382a048fd7859f85034a03d4d01e9a842629eb1aca4748757828e33a","sha256:3371ba9e8cd798d1b6675ac31cf5e646b02bc56f8332d4e2d014cc9417b55438"],"state_sha256":"fced06a7ee4661369aa22f93484a7c1e6cfedec91c603d7ee8d2f771a35e8b94"}