{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:J2ZMZNJQ2N2YA5CF7GI6JN5L74","short_pith_number":"pith:J2ZMZNJQ","schema_version":"1.0","canonical_sha256":"4eb2ccb530d375807445f991e4b7abff2c100e7e478651eb973a7d27b79d2ba9","source":{"kind":"arxiv","id":"1701.05954","version":1},"attestation_state":"computed","paper":{"title":"Learning Policies for Markov Decision Processes from Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Hao Liu, Henghui Zhu, Ioannis Ch. Paschalidis, Manjesh K. Hanawal","submitted_at":"2017-01-21T00:11:06Z","abstract_excerpt":"We consider the problem of learning a policy for a Markov decision process consistent with data captured on the state-actions pairs followed by the policy. We assume that the policy belongs to a class of parameterized policies which are defined using features associated with the state-action pairs. The features are known a priori, however, only an unknown subset of them could be relevant. The policy parameters that correspond to an observed target policy are recovered using $\\ell_1$-regularized logistic regression that best fits the observed state-action samples. We establish bounds on the dif"},"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":"1701.05954","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2017-01-21T00:11:06Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"25bc39cd8ee37e68a4c16adb5a0b305c95dec7b5277d96ed1748f6e0a9cda852","abstract_canon_sha256":"3f32f20a25bc2ab99010afdbf5be5c31a0e1b3b3a082e8c9638f01a074d37f7f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:52:19.754688Z","signature_b64":"HTNfnM/cfMmvpyELiptli4hs6nS9navr+2CzvkpuVBuJEFNCiahklrF1iSoqdFLOtN3KRiU/sEnpK87pdObrCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4eb2ccb530d375807445f991e4b7abff2c100e7e478651eb973a7d27b79d2ba9","last_reissued_at":"2026-05-18T00:52:19.754157Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:52:19.754157Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Policies for Markov Decision Processes from Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"math.OC","authors_text":"Hao Liu, Henghui Zhu, Ioannis Ch. Paschalidis, Manjesh K. Hanawal","submitted_at":"2017-01-21T00:11:06Z","abstract_excerpt":"We consider the problem of learning a policy for a Markov decision process consistent with data captured on the state-actions pairs followed by the policy. We assume that the policy belongs to a class of parameterized policies which are defined using features associated with the state-action pairs. The features are known a priori, however, only an unknown subset of them could be relevant. The policy parameters that correspond to an observed target policy are recovered using $\\ell_1$-regularized logistic regression that best fits the observed state-action samples. We establish bounds on the dif"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1701.05954","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":"1701.05954","created_at":"2026-05-18T00:52:19.754234+00:00"},{"alias_kind":"arxiv_version","alias_value":"1701.05954v1","created_at":"2026-05-18T00:52:19.754234+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1701.05954","created_at":"2026-05-18T00:52:19.754234+00:00"},{"alias_kind":"pith_short_12","alias_value":"J2ZMZNJQ2N2Y","created_at":"2026-05-18T12:31:21.493067+00:00"},{"alias_kind":"pith_short_16","alias_value":"J2ZMZNJQ2N2YA5CF","created_at":"2026-05-18T12:31:21.493067+00:00"},{"alias_kind":"pith_short_8","alias_value":"J2ZMZNJQ","created_at":"2026-05-18T12:31:21.493067+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/J2ZMZNJQ2N2YA5CF7GI6JN5L74","json":"https://pith.science/pith/J2ZMZNJQ2N2YA5CF7GI6JN5L74.json","graph_json":"https://pith.science/api/pith-number/J2ZMZNJQ2N2YA5CF7GI6JN5L74/graph.json","events_json":"https://pith.science/api/pith-number/J2ZMZNJQ2N2YA5CF7GI6JN5L74/events.json","paper":"https://pith.science/paper/J2ZMZNJQ"},"agent_actions":{"view_html":"https://pith.science/pith/J2ZMZNJQ2N2YA5CF7GI6JN5L74","download_json":"https://pith.science/pith/J2ZMZNJQ2N2YA5CF7GI6JN5L74.json","view_paper":"https://pith.science/paper/J2ZMZNJQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1701.05954&json=true","fetch_graph":"https://pith.science/api/pith-number/J2ZMZNJQ2N2YA5CF7GI6JN5L74/graph.json","fetch_events":"https://pith.science/api/pith-number/J2ZMZNJQ2N2YA5CF7GI6JN5L74/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J2ZMZNJQ2N2YA5CF7GI6JN5L74/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J2ZMZNJQ2N2YA5CF7GI6JN5L74/action/storage_attestation","attest_author":"https://pith.science/pith/J2ZMZNJQ2N2YA5CF7GI6JN5L74/action/author_attestation","sign_citation":"https://pith.science/pith/J2ZMZNJQ2N2YA5CF7GI6JN5L74/action/citation_signature","submit_replication":"https://pith.science/pith/J2ZMZNJQ2N2YA5CF7GI6JN5L74/action/replication_record"}},"created_at":"2026-05-18T00:52:19.754234+00:00","updated_at":"2026-05-18T00:52:19.754234+00:00"}