{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:VLYUJEJZIZ3UAVXBUSK2U5MLZQ","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":"f08c3bb04d9283538ed9b5048b00498e75c8c9b1425eb44bd21bdce621bbe3a2","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-09T03:50:05Z","title_canon_sha256":"aa4f44cd6a444e4d81c23eee7751df9d263ce9688554c9007471846f303fc45b"},"schema_version":"1.0","source":{"id":"2210.04157","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.04157","created_at":"2026-07-05T05:04:36Z"},{"alias_kind":"arxiv_version","alias_value":"2210.04157v1","created_at":"2026-07-05T05:04:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.04157","created_at":"2026-07-05T05:04:36Z"},{"alias_kind":"pith_short_12","alias_value":"VLYUJEJZIZ3U","created_at":"2026-07-05T05:04:36Z"},{"alias_kind":"pith_short_16","alias_value":"VLYUJEJZIZ3UAVXB","created_at":"2026-07-05T05:04:36Z"},{"alias_kind":"pith_short_8","alias_value":"VLYUJEJZ","created_at":"2026-07-05T05:04:36Z"}],"graph_snapshots":[{"event_id":"sha256:d296c32c613a06437b902873d9a78ed7f9ad49dcc119806298c17c07c28b45c4","target":"graph","created_at":"2026-07-05T05:04:36Z","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/2210.04157/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Coverage conditions -- which assert that the data logging distribution adequately covers the state space -- play a fundamental role in determining the sample complexity of offline reinforcement learning. While such conditions might seem irrelevant to online reinforcement learning at first glance, we establish a new connection by showing -- somewhat surprisingly -- that the mere existence of a data distribution with good coverage can enable sample-efficient online RL. Concretely, we show that coverability -- that is, existence of a data distribution that satisfies a ubiquitous coverage conditio","authors_text":"Dylan J. Foster, Nan Jiang, Sham M. Kakade, Tengyang Xie, Yu Bai","cross_cats":["cs.AI","math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-09T03:50:05Z","title":"The Role of Coverage in Online Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.04157","kind":"arxiv","version":1},"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":"sha256:0440885d0d7c10c2013cb869118ae111d65953f1c2f641e749e8e0b96278e181","target":"record","created_at":"2026-07-05T05:04:36Z","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":"f08c3bb04d9283538ed9b5048b00498e75c8c9b1425eb44bd21bdce621bbe3a2","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-09T03:50:05Z","title_canon_sha256":"aa4f44cd6a444e4d81c23eee7751df9d263ce9688554c9007471846f303fc45b"},"schema_version":"1.0","source":{"id":"2210.04157","kind":"arxiv","version":1}},"canonical_sha256":"aaf144913946774056e1a495aa758bcc3ab7228054b6e1e79d30ea952960f336","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aaf144913946774056e1a495aa758bcc3ab7228054b6e1e79d30ea952960f336","first_computed_at":"2026-07-05T05:04:36.895506Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:04:36.895506Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KXgbfaHCZrqocv2CEXusQJ9pj41OPyF5hCpkZd9xKEVYxmdSXBogItuxWNwHF7rLeP+ooZ0Ytujs7gnSUsi8CA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:04:36.895996Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.04157","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0440885d0d7c10c2013cb869118ae111d65953f1c2f641e749e8e0b96278e181","sha256:d296c32c613a06437b902873d9a78ed7f9ad49dcc119806298c17c07c28b45c4"],"state_sha256":"265926636590e62208b578727aab58b46b95899f8ffc3202df67b2f70cb6ec4c"}