{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LUHB2V4D27KNSEG4CBJIEH52DB","short_pith_number":"pith:LUHB2V4D","schema_version":"1.0","canonical_sha256":"5d0e1d5783d7d4d910dc1052821fba1872147a26613eeb0c4686932f1c4b9345","source":{"kind":"arxiv","id":"2505.00304","version":1},"attestation_state":"computed","paper":{"title":"Reinforcement Learning with Continuous Actions Under Unmeasured Confounding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ME"],"primary_cat":"stat.ML","authors_text":"Eugene Han, Ruoqing Zhu, Wenzhuo Zhou, Yifan Cui, Yifan Hu, Yuhan Li, Zhengling Qi","submitted_at":"2025-05-01T04:55:29Z","abstract_excerpt":"This paper addresses the challenge of offline policy learning in reinforcement learning with continuous action spaces when unmeasured confounders are present. While most existing research focuses on policy evaluation within partially observable Markov decision processes (POMDPs) and assumes discrete action spaces, we advance this field by establishing a novel identification result to enable the nonparametric estimation of policy value for a given target policy under an infinite-horizon framework. Leveraging this identification, we develop a minimax estimator and introduce a policy-gradient-bas"},"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":"2505.00304","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2025-05-01T04:55:29Z","cross_cats_sorted":["cs.LG","stat.ME"],"title_canon_sha256":"9303554271aa3767e7dd5aac3c0591f53c79fbe2d92910b4bbe7efedc5d4530c","abstract_canon_sha256":"b1e30fd0cdd97c21bc63eb166a3e435c36197771b6c429da48ae924716788f23"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:57:11.330255Z","signature_b64":"IcUiF8WeCs4qrggnAempI999KZJ3jUyH8TVno7KP2PY5L2dpQ+3lPpgshx6Z35g+amskHuZjpfXGdj34w8oKAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d0e1d5783d7d4d910dc1052821fba1872147a26613eeb0c4686932f1c4b9345","last_reissued_at":"2026-07-05T10:57:11.329823Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:57:11.329823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning with Continuous Actions Under Unmeasured Confounding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ME"],"primary_cat":"stat.ML","authors_text":"Eugene Han, Ruoqing Zhu, Wenzhuo Zhou, Yifan Cui, Yifan Hu, Yuhan Li, Zhengling Qi","submitted_at":"2025-05-01T04:55:29Z","abstract_excerpt":"This paper addresses the challenge of offline policy learning in reinforcement learning with continuous action spaces when unmeasured confounders are present. While most existing research focuses on policy evaluation within partially observable Markov decision processes (POMDPs) and assumes discrete action spaces, we advance this field by establishing a novel identification result to enable the nonparametric estimation of policy value for a given target policy under an infinite-horizon framework. Leveraging this identification, we develop a minimax estimator and introduce a policy-gradient-bas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.00304","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/2505.00304/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":"2505.00304","created_at":"2026-07-05T10:57:11.329884+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.00304v1","created_at":"2026-07-05T10:57:11.329884+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.00304","created_at":"2026-07-05T10:57:11.329884+00:00"},{"alias_kind":"pith_short_12","alias_value":"LUHB2V4D27KN","created_at":"2026-07-05T10:57:11.329884+00:00"},{"alias_kind":"pith_short_16","alias_value":"LUHB2V4D27KNSEG4","created_at":"2026-07-05T10:57:11.329884+00:00"},{"alias_kind":"pith_short_8","alias_value":"LUHB2V4D","created_at":"2026-07-05T10:57:11.329884+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/LUHB2V4D27KNSEG4CBJIEH52DB","json":"https://pith.science/pith/LUHB2V4D27KNSEG4CBJIEH52DB.json","graph_json":"https://pith.science/api/pith-number/LUHB2V4D27KNSEG4CBJIEH52DB/graph.json","events_json":"https://pith.science/api/pith-number/LUHB2V4D27KNSEG4CBJIEH52DB/events.json","paper":"https://pith.science/paper/LUHB2V4D"},"agent_actions":{"view_html":"https://pith.science/pith/LUHB2V4D27KNSEG4CBJIEH52DB","download_json":"https://pith.science/pith/LUHB2V4D27KNSEG4CBJIEH52DB.json","view_paper":"https://pith.science/paper/LUHB2V4D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.00304&json=true","fetch_graph":"https://pith.science/api/pith-number/LUHB2V4D27KNSEG4CBJIEH52DB/graph.json","fetch_events":"https://pith.science/api/pith-number/LUHB2V4D27KNSEG4CBJIEH52DB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LUHB2V4D27KNSEG4CBJIEH52DB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LUHB2V4D27KNSEG4CBJIEH52DB/action/storage_attestation","attest_author":"https://pith.science/pith/LUHB2V4D27KNSEG4CBJIEH52DB/action/author_attestation","sign_citation":"https://pith.science/pith/LUHB2V4D27KNSEG4CBJIEH52DB/action/citation_signature","submit_replication":"https://pith.science/pith/LUHB2V4D27KNSEG4CBJIEH52DB/action/replication_record"}},"created_at":"2026-07-05T10:57:11.329884+00:00","updated_at":"2026-07-05T10:57:11.329884+00:00"}