{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:AF3LSFZVR7N5PSUEDZXYSDHCLA","short_pith_number":"pith:AF3LSFZV","schema_version":"1.0","canonical_sha256":"0176b917358fdbd7ca841e6f890ce2583ba5340cf44946c36fa12e5584d796a1","source":{"kind":"arxiv","id":"2211.07614","version":1},"attestation_state":"computed","paper":{"title":"Towards Data-Driven Offline Simulations for Online Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alex Lamb, Dipendra Misra, Felipe Vieira Frujeri, John Langford, Paul Mineiro, Sebastian Kochman, Shengpu Tang","submitted_at":"2022-11-14T18:36:13Z","abstract_excerpt":"Modern decision-making systems, from robots to web recommendation engines, are expected to adapt: to user preferences, changing circumstances or even new tasks. Yet, it is still uncommon to deploy a dynamically learning agent (rather than a fixed policy) to a production system, as it's perceived as unsafe. Using historical data to reason about learning algorithms, similar to offline policy evaluation (OPE) applied to fixed policies, could help practitioners evaluate and ultimately deploy such adaptive agents to production. In this work, we formalize offline learner simulation (OLS) for reinfor"},"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":"2211.07614","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-14T18:36:13Z","cross_cats_sorted":[],"title_canon_sha256":"89e82eadef1a091ee127d5c07437d8c3e73d9fea5e147dc6de9d9085a72c7238","abstract_canon_sha256":"dc46866e6d68c3c203427c26fe172994636e7de05f217f967aa53a8c1d33ec2f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:15:55.562167Z","signature_b64":"46b+w/lVyxTdc8DWNhLJHW9ltDUtWQWDiHFHwsWqqsAkiNUQvDdkbd7QZpuDeXwj9i9EurFI7xTmFatDLHpVBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0176b917358fdbd7ca841e6f890ce2583ba5340cf44946c36fa12e5584d796a1","last_reissued_at":"2026-07-05T05:15:55.561679Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:15:55.561679Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Data-Driven Offline Simulations for Online Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alex Lamb, Dipendra Misra, Felipe Vieira Frujeri, John Langford, Paul Mineiro, Sebastian Kochman, Shengpu Tang","submitted_at":"2022-11-14T18:36:13Z","abstract_excerpt":"Modern decision-making systems, from robots to web recommendation engines, are expected to adapt: to user preferences, changing circumstances or even new tasks. Yet, it is still uncommon to deploy a dynamically learning agent (rather than a fixed policy) to a production system, as it's perceived as unsafe. Using historical data to reason about learning algorithms, similar to offline policy evaluation (OPE) applied to fixed policies, could help practitioners evaluate and ultimately deploy such adaptive agents to production. In this work, we formalize offline learner simulation (OLS) for reinfor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.07614","kind":"arxiv","version":1},"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/2211.07614/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":"2211.07614","created_at":"2026-07-05T05:15:55.561746+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.07614v1","created_at":"2026-07-05T05:15:55.561746+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.07614","created_at":"2026-07-05T05:15:55.561746+00:00"},{"alias_kind":"pith_short_12","alias_value":"AF3LSFZVR7N5","created_at":"2026-07-05T05:15:55.561746+00:00"},{"alias_kind":"pith_short_16","alias_value":"AF3LSFZVR7N5PSUE","created_at":"2026-07-05T05:15:55.561746+00:00"},{"alias_kind":"pith_short_8","alias_value":"AF3LSFZV","created_at":"2026-07-05T05:15:55.561746+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AF3LSFZVR7N5PSUEDZXYSDHCLA","json":"https://pith.science/pith/AF3LSFZVR7N5PSUEDZXYSDHCLA.json","graph_json":"https://pith.science/api/pith-number/AF3LSFZVR7N5PSUEDZXYSDHCLA/graph.json","events_json":"https://pith.science/api/pith-number/AF3LSFZVR7N5PSUEDZXYSDHCLA/events.json","paper":"https://pith.science/paper/AF3LSFZV"},"agent_actions":{"view_html":"https://pith.science/pith/AF3LSFZVR7N5PSUEDZXYSDHCLA","download_json":"https://pith.science/pith/AF3LSFZVR7N5PSUEDZXYSDHCLA.json","view_paper":"https://pith.science/paper/AF3LSFZV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.07614&json=true","fetch_graph":"https://pith.science/api/pith-number/AF3LSFZVR7N5PSUEDZXYSDHCLA/graph.json","fetch_events":"https://pith.science/api/pith-number/AF3LSFZVR7N5PSUEDZXYSDHCLA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AF3LSFZVR7N5PSUEDZXYSDHCLA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AF3LSFZVR7N5PSUEDZXYSDHCLA/action/storage_attestation","attest_author":"https://pith.science/pith/AF3LSFZVR7N5PSUEDZXYSDHCLA/action/author_attestation","sign_citation":"https://pith.science/pith/AF3LSFZVR7N5PSUEDZXYSDHCLA/action/citation_signature","submit_replication":"https://pith.science/pith/AF3LSFZVR7N5PSUEDZXYSDHCLA/action/replication_record"}},"created_at":"2026-07-05T05:15:55.561746+00:00","updated_at":"2026-07-05T05:15:55.561746+00:00"}