{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:5HXMLC5IJGRHMI2HHFQ4YOADYR","short_pith_number":"pith:5HXMLC5I","schema_version":"1.0","canonical_sha256":"e9eec58ba849a27623473961cc3803c46eb397e5acf6b6a5ea5db81fbaff0300","source":{"kind":"arxiv","id":"1710.05387","version":1},"attestation_state":"computed","paper":{"title":"Manifold Regularization for Kernelized LSTD","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Byron Boots, Krzysztof Choromanski, Vikas Sindhwani, Xinyan Yan","submitted_at":"2017-10-15T19:59:13Z","abstract_excerpt":"Policy evaluation or value function or Q-function approximation is a key procedure in reinforcement learning (RL). It is a necessary component of policy iteration and can be used for variance reduction in policy gradient methods. Therefore its quality has a significant impact on most RL algorithms. Motivated by manifold regularized learning, we propose a novel kernelized policy evaluation method that takes advantage of the intrinsic geometry of the state space learned from data, in order to achieve better sample efficiency and higher accuracy in Q-function approximation. Applying the proposed "},"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":"1710.05387","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-10-15T19:59:13Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"bd865f593abce48716abc79d3fd799cb15c783c8db6dadb195f26ff7ef6940fb","abstract_canon_sha256":"f67bf1610557958781388055af7d71929cf04650de32cca70196eb8bd27f4033"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:32:49.716982Z","signature_b64":"xvu0aIWTvH+JAWliZExjUolVK+Ps3X+4vlVe19WVBBAzXFwDUqtzNfz+WUwsM79TGZoiLF2HRa5E06nrh2RYAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e9eec58ba849a27623473961cc3803c46eb397e5acf6b6a5ea5db81fbaff0300","last_reissued_at":"2026-05-18T00:32:49.716232Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:32:49.716232Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Manifold Regularization for Kernelized LSTD","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Byron Boots, Krzysztof Choromanski, Vikas Sindhwani, Xinyan Yan","submitted_at":"2017-10-15T19:59:13Z","abstract_excerpt":"Policy evaluation or value function or Q-function approximation is a key procedure in reinforcement learning (RL). It is a necessary component of policy iteration and can be used for variance reduction in policy gradient methods. Therefore its quality has a significant impact on most RL algorithms. Motivated by manifold regularized learning, we propose a novel kernelized policy evaluation method that takes advantage of the intrinsic geometry of the state space learned from data, in order to achieve better sample efficiency and higher accuracy in Q-function approximation. Applying the proposed "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.05387","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":"1710.05387","created_at":"2026-05-18T00:32:49.716355+00:00"},{"alias_kind":"arxiv_version","alias_value":"1710.05387v1","created_at":"2026-05-18T00:32:49.716355+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.05387","created_at":"2026-05-18T00:32:49.716355+00:00"},{"alias_kind":"pith_short_12","alias_value":"5HXMLC5IJGRH","created_at":"2026-05-18T12:31:00.734936+00:00"},{"alias_kind":"pith_short_16","alias_value":"5HXMLC5IJGRHMI2H","created_at":"2026-05-18T12:31:00.734936+00:00"},{"alias_kind":"pith_short_8","alias_value":"5HXMLC5I","created_at":"2026-05-18T12:31:00.734936+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/5HXMLC5IJGRHMI2HHFQ4YOADYR","json":"https://pith.science/pith/5HXMLC5IJGRHMI2HHFQ4YOADYR.json","graph_json":"https://pith.science/api/pith-number/5HXMLC5IJGRHMI2HHFQ4YOADYR/graph.json","events_json":"https://pith.science/api/pith-number/5HXMLC5IJGRHMI2HHFQ4YOADYR/events.json","paper":"https://pith.science/paper/5HXMLC5I"},"agent_actions":{"view_html":"https://pith.science/pith/5HXMLC5IJGRHMI2HHFQ4YOADYR","download_json":"https://pith.science/pith/5HXMLC5IJGRHMI2HHFQ4YOADYR.json","view_paper":"https://pith.science/paper/5HXMLC5I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1710.05387&json=true","fetch_graph":"https://pith.science/api/pith-number/5HXMLC5IJGRHMI2HHFQ4YOADYR/graph.json","fetch_events":"https://pith.science/api/pith-number/5HXMLC5IJGRHMI2HHFQ4YOADYR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5HXMLC5IJGRHMI2HHFQ4YOADYR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5HXMLC5IJGRHMI2HHFQ4YOADYR/action/storage_attestation","attest_author":"https://pith.science/pith/5HXMLC5IJGRHMI2HHFQ4YOADYR/action/author_attestation","sign_citation":"https://pith.science/pith/5HXMLC5IJGRHMI2HHFQ4YOADYR/action/citation_signature","submit_replication":"https://pith.science/pith/5HXMLC5IJGRHMI2HHFQ4YOADYR/action/replication_record"}},"created_at":"2026-05-18T00:32:49.716355+00:00","updated_at":"2026-05-18T00:32:49.716355+00:00"}