{"paper":{"title":"Policy Optimization with Stochastic Mirror Descent","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Gang Pan, Gang Zheng, Jianhang Huang, Jun Wen, Long Yang, Pengfei Li, Qian Zheng, Yu Zhang","submitted_at":"2019-06-25T11:36:18Z","abstract_excerpt":"Improving sample efficiency has been a longstanding goal in reinforcement learning. This paper proposes $\\mathtt{VRMPO}$ algorithm: a sample efficient policy gradient method with stochastic mirror descent. In $\\mathtt{VRMPO}$, a novel variance-reduced policy gradient estimator is presented to improve sample efficiency. We prove that the proposed $\\mathtt{VRMPO}$ needs only $\\mathcal{O}(\\epsilon^{-3})$ sample trajectories to achieve an $\\epsilon$-approximate first-order stationary point, which matches the best sample complexity for policy optimization. The extensive experimental results demonst"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.10462","kind":"arxiv","version":5},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1906.10462/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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"}