{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2012:63O3O4BPZDFJIGYP2LRG56PYMN","short_pith_number":"pith:63O3O4BP","schema_version":"1.0","canonical_sha256":"f6ddb7702fc8ca941b0fd2e26ef9f8634c0bcbded5d577f7458a3ce309dbf00b","source":{"kind":"arxiv","id":"1206.6485","version":1},"attestation_state":"computed","paper":{"title":"Greedy Algorithms for Sparse Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Christopher Painter-Wakefield (Duke University), Ronald Parr (Duke University)","submitted_at":"2012-06-27T19:59:59Z","abstract_excerpt":"Feature selection and regularization are becoming increasingly prominent tools in the efforts of the reinforcement learning (RL) community to expand the reach and applicability of RL. One approach to the problem of feature selection is to impose a sparsity-inducing form of regularization on the learning method. Recent work on $L_1$ regularization has adapted techniques from the supervised learning literature for use with RL. Another approach that has received renewed attention in the supervised learning community is that of using a simple algorithm that greedily adds new features. Such algorit"},"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":"1206.6485","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-06-27T19:59:59Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"8371e3451465767108a888f48d0d4e3960b389bcc18bd8de8fa436f1927984ef","abstract_canon_sha256":"c9173fe3df57eaef755f853e2146482144838de8d1ee2d011b5145d69f233e03"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:52:13.683725Z","signature_b64":"4ExoniyAYvLkm3RW+qRIgwLEyfWn+UxexHnMsHb2t4xiQlEMOaHItlGlkI02z0qZVxW9nY1XU5chOLVUXBBGBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f6ddb7702fc8ca941b0fd2e26ef9f8634c0bcbded5d577f7458a3ce309dbf00b","last_reissued_at":"2026-05-18T03:52:13.682920Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:52:13.682920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Greedy Algorithms for Sparse Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Christopher Painter-Wakefield (Duke University), Ronald Parr (Duke University)","submitted_at":"2012-06-27T19:59:59Z","abstract_excerpt":"Feature selection and regularization are becoming increasingly prominent tools in the efforts of the reinforcement learning (RL) community to expand the reach and applicability of RL. One approach to the problem of feature selection is to impose a sparsity-inducing form of regularization on the learning method. Recent work on $L_1$ regularization has adapted techniques from the supervised learning literature for use with RL. Another approach that has received renewed attention in the supervised learning community is that of using a simple algorithm that greedily adds new features. Such algorit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1206.6485","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":"1206.6485","created_at":"2026-05-18T03:52:13.683050+00:00"},{"alias_kind":"arxiv_version","alias_value":"1206.6485v1","created_at":"2026-05-18T03:52:13.683050+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1206.6485","created_at":"2026-05-18T03:52:13.683050+00:00"},{"alias_kind":"pith_short_12","alias_value":"63O3O4BPZDFJ","created_at":"2026-05-18T12:26:56.085431+00:00"},{"alias_kind":"pith_short_16","alias_value":"63O3O4BPZDFJIGYP","created_at":"2026-05-18T12:26:56.085431+00:00"},{"alias_kind":"pith_short_8","alias_value":"63O3O4BP","created_at":"2026-05-18T12:26:56.085431+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.23056","citing_title":"K-Score: Kalman Filter as a Principled Alternative to Reward Normalization in Reinforcement Learning","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/63O3O4BPZDFJIGYP2LRG56PYMN","json":"https://pith.science/pith/63O3O4BPZDFJIGYP2LRG56PYMN.json","graph_json":"https://pith.science/api/pith-number/63O3O4BPZDFJIGYP2LRG56PYMN/graph.json","events_json":"https://pith.science/api/pith-number/63O3O4BPZDFJIGYP2LRG56PYMN/events.json","paper":"https://pith.science/paper/63O3O4BP"},"agent_actions":{"view_html":"https://pith.science/pith/63O3O4BPZDFJIGYP2LRG56PYMN","download_json":"https://pith.science/pith/63O3O4BPZDFJIGYP2LRG56PYMN.json","view_paper":"https://pith.science/paper/63O3O4BP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1206.6485&json=true","fetch_graph":"https://pith.science/api/pith-number/63O3O4BPZDFJIGYP2LRG56PYMN/graph.json","fetch_events":"https://pith.science/api/pith-number/63O3O4BPZDFJIGYP2LRG56PYMN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/63O3O4BPZDFJIGYP2LRG56PYMN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/63O3O4BPZDFJIGYP2LRG56PYMN/action/storage_attestation","attest_author":"https://pith.science/pith/63O3O4BPZDFJIGYP2LRG56PYMN/action/author_attestation","sign_citation":"https://pith.science/pith/63O3O4BPZDFJIGYP2LRG56PYMN/action/citation_signature","submit_replication":"https://pith.science/pith/63O3O4BPZDFJIGYP2LRG56PYMN/action/replication_record"}},"created_at":"2026-05-18T03:52:13.683050+00:00","updated_at":"2026-05-18T03:52:13.683050+00:00"}