{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:EC2GIAS43TSC3TTLPN6YEY245X","short_pith_number":"pith:EC2GIAS4","schema_version":"1.0","canonical_sha256":"20b464025cdce42dce6b7b7d82635cedca746fe4548dbf38fbd957e168bdac74","source":{"kind":"arxiv","id":"1812.10576","version":1},"attestation_state":"computed","paper":{"title":"Deconfounding Reinforcement Learning in Observational Settings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bernhard Sch\\\"olkopf, Chaochao Lu, Jos\\'e Miguel Hern\\'andez-Lobato","submitted_at":"2018-12-26T23:48:51Z","abstract_excerpt":"We propose a general formulation for addressing reinforcement learning (RL) problems in settings with observational data. That is, we consider the problem of learning good policies solely from historical data in which unobserved factors (confounders) affect both observed actions and rewards. Our formulation allows us to extend a representative RL algorithm, the Actor-Critic method, to its deconfounding variant, with the methodology for this extension being easily applied to other RL algorithms. In addition to this, we develop a new benchmark for evaluating deconfounding RL algorithms by modify"},"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":"1812.10576","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-26T23:48:51Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"b70409b28b834293d254572db6f664d64fa1d192a6687c6453920dc0b95d6512","abstract_canon_sha256":"476c4e025bc1cc5fd9c7bcc0d2f6c71e203b7b5707dbfed6a4d12fc70b4d548c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:57:20.618244Z","signature_b64":"/QPFxwoaKH7WuzW7fkhlXcFUZWnifpm+BZP/BO59Z6UJmGU/eKZBIR+h+2IBNhVXisBM3RO3CXdY0ntXZPWNCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"20b464025cdce42dce6b7b7d82635cedca746fe4548dbf38fbd957e168bdac74","last_reissued_at":"2026-05-17T23:57:20.617635Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:57:20.617635Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deconfounding Reinforcement Learning in Observational Settings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bernhard Sch\\\"olkopf, Chaochao Lu, Jos\\'e Miguel Hern\\'andez-Lobato","submitted_at":"2018-12-26T23:48:51Z","abstract_excerpt":"We propose a general formulation for addressing reinforcement learning (RL) problems in settings with observational data. That is, we consider the problem of learning good policies solely from historical data in which unobserved factors (confounders) affect both observed actions and rewards. Our formulation allows us to extend a representative RL algorithm, the Actor-Critic method, to its deconfounding variant, with the methodology for this extension being easily applied to other RL algorithms. In addition to this, we develop a new benchmark for evaluating deconfounding RL algorithms by modify"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.10576","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":""},"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":"1812.10576","created_at":"2026-05-17T23:57:20.617732+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.10576v1","created_at":"2026-05-17T23:57:20.617732+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.10576","created_at":"2026-05-17T23:57:20.617732+00:00"},{"alias_kind":"pith_short_12","alias_value":"EC2GIAS43TSC","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_16","alias_value":"EC2GIAS43TSC3TTL","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_8","alias_value":"EC2GIAS4","created_at":"2026-05-18T12:32:22.470017+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"1907.06584","citing_title":"Environment Reconstruction with Hidden Confounders for Reinforcement Learning based Recommendation","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12831","citing_title":"Quantifying Potential Observation Missingness in Inverse Reinforcement Learning","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06066","citing_title":"Causal Reinforcement Learning for Complex Card Games: A Magic The Gathering Benchmark","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EC2GIAS43TSC3TTLPN6YEY245X","json":"https://pith.science/pith/EC2GIAS43TSC3TTLPN6YEY245X.json","graph_json":"https://pith.science/api/pith-number/EC2GIAS43TSC3TTLPN6YEY245X/graph.json","events_json":"https://pith.science/api/pith-number/EC2GIAS43TSC3TTLPN6YEY245X/events.json","paper":"https://pith.science/paper/EC2GIAS4"},"agent_actions":{"view_html":"https://pith.science/pith/EC2GIAS43TSC3TTLPN6YEY245X","download_json":"https://pith.science/pith/EC2GIAS43TSC3TTLPN6YEY245X.json","view_paper":"https://pith.science/paper/EC2GIAS4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.10576&json=true","fetch_graph":"https://pith.science/api/pith-number/EC2GIAS43TSC3TTLPN6YEY245X/graph.json","fetch_events":"https://pith.science/api/pith-number/EC2GIAS43TSC3TTLPN6YEY245X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EC2GIAS43TSC3TTLPN6YEY245X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EC2GIAS43TSC3TTLPN6YEY245X/action/storage_attestation","attest_author":"https://pith.science/pith/EC2GIAS43TSC3TTLPN6YEY245X/action/author_attestation","sign_citation":"https://pith.science/pith/EC2GIAS43TSC3TTLPN6YEY245X/action/citation_signature","submit_replication":"https://pith.science/pith/EC2GIAS43TSC3TTLPN6YEY245X/action/replication_record"}},"created_at":"2026-05-17T23:57:20.617732+00:00","updated_at":"2026-05-17T23:57:20.617732+00:00"}