{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:2PSRDSTLMEYY34V62X6JEUSNCN","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":"697d3b3cba32242dc2241d79b06130c731ec97df2c5e4fd58d00f9eb8e3f46df","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-03-02T20:05:11Z","title_canon_sha256":"708424bdddc8fc2cd197a33d3c42d13011f0ee801c57887bf38972ec9006d776"},"schema_version":"1.0","source":{"id":"2203.01387","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.01387","created_at":"2026-07-05T06:02:27Z"},{"alias_kind":"arxiv_version","alias_value":"2203.01387v3","created_at":"2026-07-05T06:02:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.01387","created_at":"2026-07-05T06:02:27Z"},{"alias_kind":"pith_short_12","alias_value":"2PSRDSTLMEYY","created_at":"2026-07-05T06:02:27Z"},{"alias_kind":"pith_short_16","alias_value":"2PSRDSTLMEYY34V6","created_at":"2026-07-05T06:02:27Z"},{"alias_kind":"pith_short_8","alias_value":"2PSRDSTL","created_at":"2026-07-05T06:02:27Z"}],"graph_snapshots":[{"event_id":"sha256:9ce00e950d74dd04ab30fb3026c27fa5b7fd4d4037f97a127e9fabb9dc821838","target":"graph","created_at":"2026-07-05T06:02:27Z","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/2203.01387/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the widespread adoption of deep learning, reinforcement learning (RL) has experienced a dramatic increase in popularity, scaling to previously intractable problems, such as playing complex games from pixel observations, sustaining conversations with humans, and controlling robotic agents. However, there is still a wide range of domains inaccessible to RL due to the high cost and danger of interacting with the environment. Offline RL is a paradigm that learns exclusively from static datasets of previously collected interactions, making it feasible to extract policies from large and diverse","authors_text":"Esther Luna Colombini, Marcos R. O. A. Maximo, Rafael Figueiredo Prudencio","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-03-02T20:05:11Z","title":"A Survey on Offline Reinforcement Learning: Taxonomy, Review, and Open Problems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.01387","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":"sha256:4f761906984640b2db1a32c2e48294d701694099498be5a75de7aed73bf02997","target":"record","created_at":"2026-07-05T06:02:27Z","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":"697d3b3cba32242dc2241d79b06130c731ec97df2c5e4fd58d00f9eb8e3f46df","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-03-02T20:05:11Z","title_canon_sha256":"708424bdddc8fc2cd197a33d3c42d13011f0ee801c57887bf38972ec9006d776"},"schema_version":"1.0","source":{"id":"2203.01387","kind":"arxiv","version":3}},"canonical_sha256":"d3e511ca6b61318df2bed5fc92524d136e4a10f21bbf09146d3413ced300880b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d3e511ca6b61318df2bed5fc92524d136e4a10f21bbf09146d3413ced300880b","first_computed_at":"2026-07-05T06:02:27.580469Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:02:27.580469Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FJ/hIiIhF/LvWjpBT24R30i9CvOLmKJSHJuZJ+Jkas7WgYcjh8VBK7xJb3iba2Du0mbNYI5T0TKUnDTD/q0VBg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:02:27.580844Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.01387","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4f761906984640b2db1a32c2e48294d701694099498be5a75de7aed73bf02997","sha256:9ce00e950d74dd04ab30fb3026c27fa5b7fd4d4037f97a127e9fabb9dc821838"],"state_sha256":"96f30d565bc5d26c63287022b4a8aa37706ae3da0d914b808ec4aaadb74cefc0"}