{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:R3QOSOAWKCS76L2KUZ32PK26DY","short_pith_number":"pith:R3QOSOAW","schema_version":"1.0","canonical_sha256":"8ee0e9381650a5ff2f4aa677a7ab5e1e1092177630b2c86079864fc3299ff7a2","source":{"kind":"arxiv","id":"1804.10328","version":1},"attestation_state":"computed","paper":{"title":"Scalable Bilinear $\\pi$ Learning Using State and Action Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Lihong Li, Mengdi Wang, Yichen Chen","submitted_at":"2018-04-27T02:32:18Z","abstract_excerpt":"Approximate linear programming (ALP) represents one of the major algorithmic families to solve large-scale Markov decision processes (MDP). In this work, we study a primal-dual formulation of the ALP, and develop a scalable, model-free algorithm called bilinear $\\pi$ learning for reinforcement learning when a sampling oracle is provided. This algorithm enjoys a number of advantages. First, it adopts (bi)linear models to represent the high-dimensional value function and state-action distributions, using given state and action features. Its run-time complexity depends on the number of features, "},"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":"1804.10328","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-27T02:32:18Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"8e271ed318ed1096caede574f51961464e55ee47f823bec171a7cad4a215f564","abstract_canon_sha256":"eeb582ea0e1a94ebaaea33c35cdc09db569648ee661c11a1bfda7a7f58e67f3e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:17:21.080488Z","signature_b64":"Ft+xjshp6j2JBC/2nMEsZ18roMwWHOJ9zkhlUDYOLyScNtZu10EGy/x26vwDTeMU//zXyXB5KILBcrDSWZECCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ee0e9381650a5ff2f4aa677a7ab5e1e1092177630b2c86079864fc3299ff7a2","last_reissued_at":"2026-05-18T00:17:21.079995Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:17:21.079995Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scalable Bilinear $\\pi$ Learning Using State and Action Features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Lihong Li, Mengdi Wang, Yichen Chen","submitted_at":"2018-04-27T02:32:18Z","abstract_excerpt":"Approximate linear programming (ALP) represents one of the major algorithmic families to solve large-scale Markov decision processes (MDP). In this work, we study a primal-dual formulation of the ALP, and develop a scalable, model-free algorithm called bilinear $\\pi$ learning for reinforcement learning when a sampling oracle is provided. This algorithm enjoys a number of advantages. First, it adopts (bi)linear models to represent the high-dimensional value function and state-action distributions, using given state and action features. Its run-time complexity depends on the number of features, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.10328","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":"1804.10328","created_at":"2026-05-18T00:17:21.080068+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.10328v1","created_at":"2026-05-18T00:17:21.080068+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.10328","created_at":"2026-05-18T00:17:21.080068+00:00"},{"alias_kind":"pith_short_12","alias_value":"R3QOSOAWKCS7","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_16","alias_value":"R3QOSOAWKCS76L2K","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_8","alias_value":"R3QOSOAW","created_at":"2026-05-18T12:32:50.500415+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/R3QOSOAWKCS76L2KUZ32PK26DY","json":"https://pith.science/pith/R3QOSOAWKCS76L2KUZ32PK26DY.json","graph_json":"https://pith.science/api/pith-number/R3QOSOAWKCS76L2KUZ32PK26DY/graph.json","events_json":"https://pith.science/api/pith-number/R3QOSOAWKCS76L2KUZ32PK26DY/events.json","paper":"https://pith.science/paper/R3QOSOAW"},"agent_actions":{"view_html":"https://pith.science/pith/R3QOSOAWKCS76L2KUZ32PK26DY","download_json":"https://pith.science/pith/R3QOSOAWKCS76L2KUZ32PK26DY.json","view_paper":"https://pith.science/paper/R3QOSOAW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.10328&json=true","fetch_graph":"https://pith.science/api/pith-number/R3QOSOAWKCS76L2KUZ32PK26DY/graph.json","fetch_events":"https://pith.science/api/pith-number/R3QOSOAWKCS76L2KUZ32PK26DY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R3QOSOAWKCS76L2KUZ32PK26DY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R3QOSOAWKCS76L2KUZ32PK26DY/action/storage_attestation","attest_author":"https://pith.science/pith/R3QOSOAWKCS76L2KUZ32PK26DY/action/author_attestation","sign_citation":"https://pith.science/pith/R3QOSOAWKCS76L2KUZ32PK26DY/action/citation_signature","submit_replication":"https://pith.science/pith/R3QOSOAWKCS76L2KUZ32PK26DY/action/replication_record"}},"created_at":"2026-05-18T00:17:21.080068+00:00","updated_at":"2026-05-18T00:17:21.080068+00:00"}