{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:R3QOSOAWKCS76L2KUZ32PK26DY","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"eeb582ea0e1a94ebaaea33c35cdc09db569648ee661c11a1bfda7a7f58e67f3e","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-27T02:32:18Z","title_canon_sha256":"8e271ed318ed1096caede574f51961464e55ee47f823bec171a7cad4a215f564"},"schema_version":"1.0","source":{"id":"1804.10328","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.10328","created_at":"2026-05-18T00:17:21Z"},{"alias_kind":"arxiv_version","alias_value":"1804.10328v1","created_at":"2026-05-18T00:17:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.10328","created_at":"2026-05-18T00:17:21Z"},{"alias_kind":"pith_short_12","alias_value":"R3QOSOAWKCS7","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"R3QOSOAWKCS76L2K","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"R3QOSOAW","created_at":"2026-05-18T12:32:50Z"}],"graph_snapshots":[{"event_id":"sha256:4510d69689044a726d87665fbecbc376239e16d567b4bfff1c6d22ab498c0225","target":"graph","created_at":"2026-05-18T00:17:21Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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, ","authors_text":"Lihong Li, Mengdi Wang, Yichen Chen","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-27T02:32:18Z","title":"Scalable Bilinear $\\pi$ Learning Using State and Action Features"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.10328","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:eef727a31d7daae431426cd4910c46f55d8e5c9a4c0d10357b72e02e85d65b1d","target":"record","created_at":"2026-05-18T00:17:21Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"eeb582ea0e1a94ebaaea33c35cdc09db569648ee661c11a1bfda7a7f58e67f3e","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-04-27T02:32:18Z","title_canon_sha256":"8e271ed318ed1096caede574f51961464e55ee47f823bec171a7cad4a215f564"},"schema_version":"1.0","source":{"id":"1804.10328","kind":"arxiv","version":1}},"canonical_sha256":"8ee0e9381650a5ff2f4aa677a7ab5e1e1092177630b2c86079864fc3299ff7a2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8ee0e9381650a5ff2f4aa677a7ab5e1e1092177630b2c86079864fc3299ff7a2","first_computed_at":"2026-05-18T00:17:21.079995Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:17:21.079995Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ft+xjshp6j2JBC/2nMEsZ18roMwWHOJ9zkhlUDYOLyScNtZu10EGy/x26vwDTeMU//zXyXB5KILBcrDSWZECCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:17:21.080488Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.10328","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eef727a31d7daae431426cd4910c46f55d8e5c9a4c0d10357b72e02e85d65b1d","sha256:4510d69689044a726d87665fbecbc376239e16d567b4bfff1c6d22ab498c0225"],"state_sha256":"fe51167ff99a17a693c01cc00f8321bac05b00294144e476783f795c754bd289"}