{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:HEKQVKRGDZN2UPXMKKRHBVD5GW","short_pith_number":"pith:HEKQVKRG","schema_version":"1.0","canonical_sha256":"39150aaa261e5baa3eec52a270d47d358c9c198f5b489189e67e825e1e2e5e0d","source":{"kind":"arxiv","id":"1708.01298","version":1},"attestation_state":"computed","paper":{"title":"Effective sketching methods for value function approximation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Erfan Sadeqi Azer, Martha White, Yangchen Pan","submitted_at":"2017-08-03T20:27:45Z","abstract_excerpt":"High-dimensional representations, such as radial basis function networks or tile coding, are common choices for policy evaluation in reinforcement learning. Learning with such high-dimensional representations, however, can be expensive, particularly for matrix methods, such as least-squares temporal difference learning or quasi-Newton methods that approximate matrix step-sizes. In this work, we explore the utility of sketching for these two classes of algorithms. We highlight issues with sketching the high-dimensional features directly, which can incur significant bias. As a remedy, we demonst"},"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":"1708.01298","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-08-03T20:27:45Z","cross_cats_sorted":[],"title_canon_sha256":"10b899f0af65b00892d846f5541ebf0411424a4d1a4f061157bfb649c8511fb7","abstract_canon_sha256":"a1b335036a356ab1f15e9ed1148dbb95aa7414d0342d88450a95600a5bc6330e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:38:37.764062Z","signature_b64":"CRZnHnqY6uoFBPyBXGPryrDI+jrfPJz6bpG9rPB/9zcOzTiyoyIDy1xePJxKaq96L5AKm9ACk1pUzKfWVYJhDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"39150aaa261e5baa3eec52a270d47d358c9c198f5b489189e67e825e1e2e5e0d","last_reissued_at":"2026-05-18T00:38:37.763479Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:38:37.763479Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Effective sketching methods for value function approximation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Erfan Sadeqi Azer, Martha White, Yangchen Pan","submitted_at":"2017-08-03T20:27:45Z","abstract_excerpt":"High-dimensional representations, such as radial basis function networks or tile coding, are common choices for policy evaluation in reinforcement learning. Learning with such high-dimensional representations, however, can be expensive, particularly for matrix methods, such as least-squares temporal difference learning or quasi-Newton methods that approximate matrix step-sizes. In this work, we explore the utility of sketching for these two classes of algorithms. We highlight issues with sketching the high-dimensional features directly, which can incur significant bias. As a remedy, we demonst"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.01298","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":"1708.01298","created_at":"2026-05-18T00:38:37.763559+00:00"},{"alias_kind":"arxiv_version","alias_value":"1708.01298v1","created_at":"2026-05-18T00:38:37.763559+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.01298","created_at":"2026-05-18T00:38:37.763559+00:00"},{"alias_kind":"pith_short_12","alias_value":"HEKQVKRGDZN2","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_16","alias_value":"HEKQVKRGDZN2UPXM","created_at":"2026-05-18T12:31:18.294218+00:00"},{"alias_kind":"pith_short_8","alias_value":"HEKQVKRG","created_at":"2026-05-18T12:31:18.294218+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/HEKQVKRGDZN2UPXMKKRHBVD5GW","json":"https://pith.science/pith/HEKQVKRGDZN2UPXMKKRHBVD5GW.json","graph_json":"https://pith.science/api/pith-number/HEKQVKRGDZN2UPXMKKRHBVD5GW/graph.json","events_json":"https://pith.science/api/pith-number/HEKQVKRGDZN2UPXMKKRHBVD5GW/events.json","paper":"https://pith.science/paper/HEKQVKRG"},"agent_actions":{"view_html":"https://pith.science/pith/HEKQVKRGDZN2UPXMKKRHBVD5GW","download_json":"https://pith.science/pith/HEKQVKRGDZN2UPXMKKRHBVD5GW.json","view_paper":"https://pith.science/paper/HEKQVKRG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1708.01298&json=true","fetch_graph":"https://pith.science/api/pith-number/HEKQVKRGDZN2UPXMKKRHBVD5GW/graph.json","fetch_events":"https://pith.science/api/pith-number/HEKQVKRGDZN2UPXMKKRHBVD5GW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HEKQVKRGDZN2UPXMKKRHBVD5GW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HEKQVKRGDZN2UPXMKKRHBVD5GW/action/storage_attestation","attest_author":"https://pith.science/pith/HEKQVKRGDZN2UPXMKKRHBVD5GW/action/author_attestation","sign_citation":"https://pith.science/pith/HEKQVKRGDZN2UPXMKKRHBVD5GW/action/citation_signature","submit_replication":"https://pith.science/pith/HEKQVKRGDZN2UPXMKKRHBVD5GW/action/replication_record"}},"created_at":"2026-05-18T00:38:37.763559+00:00","updated_at":"2026-05-18T00:38:37.763559+00:00"}