{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:J2ZMZNJQ2N2YA5CF7GI6JN5L74","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":"3f32f20a25bc2ab99010afdbf5be5c31a0e1b3b3a082e8c9638f01a074d37f7f","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2017-01-21T00:11:06Z","title_canon_sha256":"25bc39cd8ee37e68a4c16adb5a0b305c95dec7b5277d96ed1748f6e0a9cda852"},"schema_version":"1.0","source":{"id":"1701.05954","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1701.05954","created_at":"2026-05-18T00:52:19Z"},{"alias_kind":"arxiv_version","alias_value":"1701.05954v1","created_at":"2026-05-18T00:52:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1701.05954","created_at":"2026-05-18T00:52:19Z"},{"alias_kind":"pith_short_12","alias_value":"J2ZMZNJQ2N2Y","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_16","alias_value":"J2ZMZNJQ2N2YA5CF","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_8","alias_value":"J2ZMZNJQ","created_at":"2026-05-18T12:31:21Z"}],"graph_snapshots":[{"event_id":"sha256:ce507fbdc06693c67f884dbf9d46e12330a3a1198236bb8c824874b3f8fc0546","target":"graph","created_at":"2026-05-18T00:52:19Z","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":"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","authors_text":"Hao Liu, Henghui Zhu, Ioannis Ch. Paschalidis, Manjesh K. Hanawal","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2017-01-21T00:11:06Z","title":"Learning Policies for Markov Decision Processes from Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1701.05954","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":"sha256:0cd2b49f269d29df0c07d9bedf66d50e6a72513100fcc669046d4811be771c6c","target":"record","created_at":"2026-05-18T00:52:19Z","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":"3f32f20a25bc2ab99010afdbf5be5c31a0e1b3b3a082e8c9638f01a074d37f7f","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2017-01-21T00:11:06Z","title_canon_sha256":"25bc39cd8ee37e68a4c16adb5a0b305c95dec7b5277d96ed1748f6e0a9cda852"},"schema_version":"1.0","source":{"id":"1701.05954","kind":"arxiv","version":1}},"canonical_sha256":"4eb2ccb530d375807445f991e4b7abff2c100e7e478651eb973a7d27b79d2ba9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4eb2ccb530d375807445f991e4b7abff2c100e7e478651eb973a7d27b79d2ba9","first_computed_at":"2026-05-18T00:52:19.754157Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:52:19.754157Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HTNfnM/cfMmvpyELiptli4hs6nS9navr+2CzvkpuVBuJEFNCiahklrF1iSoqdFLOtN3KRiU/sEnpK87pdObrCg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:52:19.754688Z","signed_message":"canonical_sha256_bytes"},"source_id":"1701.05954","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0cd2b49f269d29df0c07d9bedf66d50e6a72513100fcc669046d4811be771c6c","sha256:ce507fbdc06693c67f884dbf9d46e12330a3a1198236bb8c824874b3f8fc0546"],"state_sha256":"d648784f7765db99567afdf573f6779efb7f3a32f41bc3791e6acb3b1b6249b6"}