{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:GVBNVF6NR2LQTFS6AX4SJC3B77","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":"c17b90535a1d5596ad70442be816d6c10a666ca52c842da0d2df792d35583198","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-07-13T16:30:01Z","title_canon_sha256":"1ad5975ac1dd48f38055a8ccfb6d45d4c5a7be5199d075418ce7cd739d6fda37"},"schema_version":"1.0","source":{"id":"2107.06226","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.06226","created_at":"2026-07-05T05:31:43Z"},{"alias_kind":"arxiv_version","alias_value":"2107.06226v4","created_at":"2026-07-05T05:31:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.06226","created_at":"2026-07-05T05:31:43Z"},{"alias_kind":"pith_short_12","alias_value":"GVBNVF6NR2LQ","created_at":"2026-07-05T05:31:43Z"},{"alias_kind":"pith_short_16","alias_value":"GVBNVF6NR2LQTFS6","created_at":"2026-07-05T05:31:43Z"},{"alias_kind":"pith_short_8","alias_value":"GVBNVF6N","created_at":"2026-07-05T05:31:43Z"}],"graph_snapshots":[{"event_id":"sha256:7455709e75ffc264990125354bf2375607d5874bd5e072499b0200a27891e8c1","target":"graph","created_at":"2026-07-05T05:31:43Z","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/2107.06226/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study model-based offline Reinforcement Learning with general function approximation without a full coverage assumption on the offline data distribution. We present an algorithm named Constrained Pessimistic Policy Optimization (CPPO)which leverages a general function class and uses a constraint over the model class to encode pessimism. Under the assumption that the ground truth model belongs to our function class (i.e., realizability in the function class), CPPO has a PAC guarantee with offline data only providing partial coverage, i.e., it can learn a policy that competes against any poli","authors_text":"Masatoshi Uehara, Wen Sun","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-07-13T16:30:01Z","title":"Pessimistic Model-based Offline Reinforcement Learning under Partial Coverage"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.06226","kind":"arxiv","version":4},"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":"sha256:4fd4da04c7c35b142600f9912aa07984acc6b127ce969afdbad978d84bc3b864","target":"record","created_at":"2026-07-05T05:31:43Z","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":"c17b90535a1d5596ad70442be816d6c10a666ca52c842da0d2df792d35583198","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-07-13T16:30:01Z","title_canon_sha256":"1ad5975ac1dd48f38055a8ccfb6d45d4c5a7be5199d075418ce7cd739d6fda37"},"schema_version":"1.0","source":{"id":"2107.06226","kind":"arxiv","version":4}},"canonical_sha256":"3542da97cd8e9709965e05f9248b61ffd5003761809d57500f3229751f3b1b61","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3542da97cd8e9709965e05f9248b61ffd5003761809d57500f3229751f3b1b61","first_computed_at":"2026-07-05T05:31:43.496290Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:31:43.496290Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oXNma4Fev7E8dv+lqxBWrdrkJB2Ap75DgEt3i6n4z2nF9VeaRuMFsTe1E0Ho7rcQ3ByiCE5KDswwD9ul3Z2MCg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:31:43.496817Z","signed_message":"canonical_sha256_bytes"},"source_id":"2107.06226","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4fd4da04c7c35b142600f9912aa07984acc6b127ce969afdbad978d84bc3b864","sha256:7455709e75ffc264990125354bf2375607d5874bd5e072499b0200a27891e8c1"],"state_sha256":"680126f434c3eb90bf1b259b6c946e6dd3e78395fccae90b8448fa5f5fed8fcc"}