{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:RQLJI4HXU4VFNODFAWCHVH2ANU","short_pith_number":"pith:RQLJI4HX","schema_version":"1.0","canonical_sha256":"8c169470f7a72a56b86505847a9f406d285d39841422079aac986e9e6cc9fdad","source":{"kind":"arxiv","id":"1404.4258","version":2},"attestation_state":"computed","paper":{"title":"An Analysis of State-Relevance Weights and Sampling Distributions on L1-Regularized Approximate Linear Programming Approximation Accuracy","license":"http://creativecommons.org/licenses/publicdomain/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Connor Geer, David Piekut, Gavin Taylor","submitted_at":"2014-04-16T14:15:43Z","abstract_excerpt":"Recent interest in the use of $L_1$ regularization in the use of value function approximation includes Petrik et al.'s introduction of $L_1$-Regularized Approximate Linear Programming (RALP). RALP is unique among $L_1$-regularized approaches in that it approximates the optimal value function using off-policy samples. Additionally, it produces policies which outperform those of previous methods, such as LSPI. RALP's value function approximation quality is affected heavily by the choice of state-relevance weights in the objective function of the linear program, and by the distribution from which"},"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":"1404.4258","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/publicdomain/","primary_cat":"cs.AI","submitted_at":"2014-04-16T14:15:43Z","cross_cats_sorted":[],"title_canon_sha256":"d7dc009ee93ca981ebc1cfabe1d317b2fd8cf94d87d28012282b7bf63ab8a210","abstract_canon_sha256":"e667e49064d548aaa7beb6a45950d66816615c9e668d0d59e0728f1b38ff487d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:53:26.404755Z","signature_b64":"uwR0oxwpDip/9pfmp8GvbF2SmmmVpTeQmcpT3mWvhYUBBrvDm9BbncV8cHl0uLLaqf4en8kYIcx/UsfqI08xAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c169470f7a72a56b86505847a9f406d285d39841422079aac986e9e6cc9fdad","last_reissued_at":"2026-05-18T02:53:26.403967Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:53:26.403967Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Analysis of State-Relevance Weights and Sampling Distributions on L1-Regularized Approximate Linear Programming Approximation Accuracy","license":"http://creativecommons.org/licenses/publicdomain/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Connor Geer, David Piekut, Gavin Taylor","submitted_at":"2014-04-16T14:15:43Z","abstract_excerpt":"Recent interest in the use of $L_1$ regularization in the use of value function approximation includes Petrik et al.'s introduction of $L_1$-Regularized Approximate Linear Programming (RALP). RALP is unique among $L_1$-regularized approaches in that it approximates the optimal value function using off-policy samples. Additionally, it produces policies which outperform those of previous methods, such as LSPI. RALP's value function approximation quality is affected heavily by the choice of state-relevance weights in the objective function of the linear program, and by the distribution from which"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1404.4258","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":""},"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":"1404.4258","created_at":"2026-05-18T02:53:26.404100+00:00"},{"alias_kind":"arxiv_version","alias_value":"1404.4258v2","created_at":"2026-05-18T02:53:26.404100+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1404.4258","created_at":"2026-05-18T02:53:26.404100+00:00"},{"alias_kind":"pith_short_12","alias_value":"RQLJI4HXU4VF","created_at":"2026-05-18T12:28:46.137349+00:00"},{"alias_kind":"pith_short_16","alias_value":"RQLJI4HXU4VFNODF","created_at":"2026-05-18T12:28:46.137349+00:00"},{"alias_kind":"pith_short_8","alias_value":"RQLJI4HX","created_at":"2026-05-18T12:28:46.137349+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/RQLJI4HXU4VFNODFAWCHVH2ANU","json":"https://pith.science/pith/RQLJI4HXU4VFNODFAWCHVH2ANU.json","graph_json":"https://pith.science/api/pith-number/RQLJI4HXU4VFNODFAWCHVH2ANU/graph.json","events_json":"https://pith.science/api/pith-number/RQLJI4HXU4VFNODFAWCHVH2ANU/events.json","paper":"https://pith.science/paper/RQLJI4HX"},"agent_actions":{"view_html":"https://pith.science/pith/RQLJI4HXU4VFNODFAWCHVH2ANU","download_json":"https://pith.science/pith/RQLJI4HXU4VFNODFAWCHVH2ANU.json","view_paper":"https://pith.science/paper/RQLJI4HX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1404.4258&json=true","fetch_graph":"https://pith.science/api/pith-number/RQLJI4HXU4VFNODFAWCHVH2ANU/graph.json","fetch_events":"https://pith.science/api/pith-number/RQLJI4HXU4VFNODFAWCHVH2ANU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RQLJI4HXU4VFNODFAWCHVH2ANU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RQLJI4HXU4VFNODFAWCHVH2ANU/action/storage_attestation","attest_author":"https://pith.science/pith/RQLJI4HXU4VFNODFAWCHVH2ANU/action/author_attestation","sign_citation":"https://pith.science/pith/RQLJI4HXU4VFNODFAWCHVH2ANU/action/citation_signature","submit_replication":"https://pith.science/pith/RQLJI4HXU4VFNODFAWCHVH2ANU/action/replication_record"}},"created_at":"2026-05-18T02:53:26.404100+00:00","updated_at":"2026-05-18T02:53:26.404100+00:00"}