{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:557XDQL3ZX4W6TYYMER3WZLMM2","short_pith_number":"pith:557XDQL3","schema_version":"1.0","canonical_sha256":"ef7f71c17bcdf96f4f186123bb656c66b262e561214e642e94e8ec1391a5aec5","source":{"kind":"arxiv","id":"2206.02887","version":2},"attestation_state":"computed","paper":{"title":"Sample Complexity of Nonparametric Off-Policy Evaluation on Low-Dimensional Manifolds using Deep Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Mengdi Wang, Minshuo Chen, Tuo Zhao, Xiang Ji","submitted_at":"2022-06-06T20:25:20Z","abstract_excerpt":"We consider the off-policy evaluation problem of reinforcement learning using deep convolutional neural networks. We analyze the deep fitted Q-evaluation method for estimating the expected cumulative reward of a target policy, when the data are generated from an unknown behavior policy. We show that, by choosing network size appropriately, one can leverage any low-dimensional manifold structure in the Markov decision process and obtain a sample-efficient estimator without suffering from the curse of high data ambient dimensionality. Specifically, we establish a sharp error bound for fitted Q-e"},"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":"2206.02887","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-06T20:25:20Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"8821fbde070b43d82f5963d3d4945edff8bed503dd9f534eda1e65b18e2cf2be","abstract_canon_sha256":"cb7ab4279d1afa5f77f702070f3c31025042e63fd7c0eed14eede64525e5ddb8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:03:01.526022Z","signature_b64":"O2vhM8+RKZDUlI3YAYxk+LHrM2v3iIRacXQeaJWPl598Y03W+9wttgRtp7exULoubLy/IR9V5kXJU/bQJA0BDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef7f71c17bcdf96f4f186123bb656c66b262e561214e642e94e8ec1391a5aec5","last_reissued_at":"2026-07-05T05:03:01.525617Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:03:01.525617Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sample Complexity of Nonparametric Off-Policy Evaluation on Low-Dimensional Manifolds using Deep Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Mengdi Wang, Minshuo Chen, Tuo Zhao, Xiang Ji","submitted_at":"2022-06-06T20:25:20Z","abstract_excerpt":"We consider the off-policy evaluation problem of reinforcement learning using deep convolutional neural networks. We analyze the deep fitted Q-evaluation method for estimating the expected cumulative reward of a target policy, when the data are generated from an unknown behavior policy. We show that, by choosing network size appropriately, one can leverage any low-dimensional manifold structure in the Markov decision process and obtain a sample-efficient estimator without suffering from the curse of high data ambient dimensionality. Specifically, we establish a sharp error bound for fitted Q-e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.02887","kind":"arxiv","version":2},"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/2206.02887/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":"2206.02887","created_at":"2026-07-05T05:03:01.525681+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.02887v2","created_at":"2026-07-05T05:03:01.525681+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.02887","created_at":"2026-07-05T05:03:01.525681+00:00"},{"alias_kind":"pith_short_12","alias_value":"557XDQL3ZX4W","created_at":"2026-07-05T05:03:01.525681+00:00"},{"alias_kind":"pith_short_16","alias_value":"557XDQL3ZX4W6TYY","created_at":"2026-07-05T05:03:01.525681+00:00"},{"alias_kind":"pith_short_8","alias_value":"557XDQL3","created_at":"2026-07-05T05:03:01.525681+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/557XDQL3ZX4W6TYYMER3WZLMM2","json":"https://pith.science/pith/557XDQL3ZX4W6TYYMER3WZLMM2.json","graph_json":"https://pith.science/api/pith-number/557XDQL3ZX4W6TYYMER3WZLMM2/graph.json","events_json":"https://pith.science/api/pith-number/557XDQL3ZX4W6TYYMER3WZLMM2/events.json","paper":"https://pith.science/paper/557XDQL3"},"agent_actions":{"view_html":"https://pith.science/pith/557XDQL3ZX4W6TYYMER3WZLMM2","download_json":"https://pith.science/pith/557XDQL3ZX4W6TYYMER3WZLMM2.json","view_paper":"https://pith.science/paper/557XDQL3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.02887&json=true","fetch_graph":"https://pith.science/api/pith-number/557XDQL3ZX4W6TYYMER3WZLMM2/graph.json","fetch_events":"https://pith.science/api/pith-number/557XDQL3ZX4W6TYYMER3WZLMM2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/557XDQL3ZX4W6TYYMER3WZLMM2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/557XDQL3ZX4W6TYYMER3WZLMM2/action/storage_attestation","attest_author":"https://pith.science/pith/557XDQL3ZX4W6TYYMER3WZLMM2/action/author_attestation","sign_citation":"https://pith.science/pith/557XDQL3ZX4W6TYYMER3WZLMM2/action/citation_signature","submit_replication":"https://pith.science/pith/557XDQL3ZX4W6TYYMER3WZLMM2/action/replication_record"}},"created_at":"2026-07-05T05:03:01.525681+00:00","updated_at":"2026-07-05T05:03:01.525681+00:00"}