{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:2PSRDSTLMEYY34V62X6JEUSNCN","short_pith_number":"pith:2PSRDSTL","schema_version":"1.0","canonical_sha256":"d3e511ca6b61318df2bed5fc92524d136e4a10f21bbf09146d3413ced300880b","source":{"kind":"arxiv","id":"2203.01387","version":3},"attestation_state":"computed","paper":{"title":"A Survey on Offline Reinforcement Learning: Taxonomy, Review, and Open Problems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Esther Luna Colombini, Marcos R. O. A. Maximo, Rafael Figueiredo Prudencio","submitted_at":"2022-03-02T20:05:11Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2203.01387","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-03-02T20:05:11Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"708424bdddc8fc2cd197a33d3c42d13011f0ee801c57887bf38972ec9006d776","abstract_canon_sha256":"697d3b3cba32242dc2241d79b06130c731ec97df2c5e4fd58d00f9eb8e3f46df"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:02:27.580844Z","signature_b64":"FJ/hIiIhF/LvWjpBT24R30i9CvOLmKJSHJuZJ+Jkas7WgYcjh8VBK7xJb3iba2Du0mbNYI5T0TKUnDTD/q0VBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d3e511ca6b61318df2bed5fc92524d136e4a10f21bbf09146d3413ced300880b","last_reissued_at":"2026-07-05T06:02:27.580469Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:02:27.580469Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey on Offline Reinforcement Learning: Taxonomy, Review, and Open Problems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Esther Luna Colombini, Marcos R. O. A. Maximo, Rafael Figueiredo Prudencio","submitted_at":"2022-03-02T20:05:11Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.01387","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2203.01387/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2203.01387","created_at":"2026-07-05T06:02:27.580535+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.01387v3","created_at":"2026-07-05T06:02:27.580535+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.01387","created_at":"2026-07-05T06:02:27.580535+00:00"},{"alias_kind":"pith_short_12","alias_value":"2PSRDSTLMEYY","created_at":"2026-07-05T06:02:27.580535+00:00"},{"alias_kind":"pith_short_16","alias_value":"2PSRDSTLMEYY34V6","created_at":"2026-07-05T06:02:27.580535+00:00"},{"alias_kind":"pith_short_8","alias_value":"2PSRDSTL","created_at":"2026-07-05T06:02:27.580535+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.14444","citing_title":"Statistical and Algorithmic Foundations of Reinforcement Learning","ref_index":86,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2PSRDSTLMEYY34V62X6JEUSNCN","json":"https://pith.science/pith/2PSRDSTLMEYY34V62X6JEUSNCN.json","graph_json":"https://pith.science/api/pith-number/2PSRDSTLMEYY34V62X6JEUSNCN/graph.json","events_json":"https://pith.science/api/pith-number/2PSRDSTLMEYY34V62X6JEUSNCN/events.json","paper":"https://pith.science/paper/2PSRDSTL"},"agent_actions":{"view_html":"https://pith.science/pith/2PSRDSTLMEYY34V62X6JEUSNCN","download_json":"https://pith.science/pith/2PSRDSTLMEYY34V62X6JEUSNCN.json","view_paper":"https://pith.science/paper/2PSRDSTL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.01387&json=true","fetch_graph":"https://pith.science/api/pith-number/2PSRDSTLMEYY34V62X6JEUSNCN/graph.json","fetch_events":"https://pith.science/api/pith-number/2PSRDSTLMEYY34V62X6JEUSNCN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2PSRDSTLMEYY34V62X6JEUSNCN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2PSRDSTLMEYY34V62X6JEUSNCN/action/storage_attestation","attest_author":"https://pith.science/pith/2PSRDSTLMEYY34V62X6JEUSNCN/action/author_attestation","sign_citation":"https://pith.science/pith/2PSRDSTLMEYY34V62X6JEUSNCN/action/citation_signature","submit_replication":"https://pith.science/pith/2PSRDSTLMEYY34V62X6JEUSNCN/action/replication_record"}},"created_at":"2026-07-05T06:02:27.580535+00:00","updated_at":"2026-07-05T06:02:27.580535+00:00"}