{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:XKHVKM3HIRXSM46ASJUDG326IV","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":"f875aaeaf08c4562916aaa942b2c117733147965772141e1959bf148159226f8","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-25T11:36:18Z","title_canon_sha256":"de562ce0dff637a117dbfda371979beacd3c3fbc525ddf3c650af9045c5e5ed7"},"schema_version":"1.0","source":{"id":"1906.10462","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.10462","created_at":"2026-07-05T03:55:23Z"},{"alias_kind":"arxiv_version","alias_value":"1906.10462v5","created_at":"2026-07-05T03:55:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.10462","created_at":"2026-07-05T03:55:23Z"},{"alias_kind":"pith_short_12","alias_value":"XKHVKM3HIRXS","created_at":"2026-07-05T03:55:23Z"},{"alias_kind":"pith_short_16","alias_value":"XKHVKM3HIRXSM46A","created_at":"2026-07-05T03:55:23Z"},{"alias_kind":"pith_short_8","alias_value":"XKHVKM3H","created_at":"2026-07-05T03:55:23Z"}],"graph_snapshots":[{"event_id":"sha256:a1c66ce99c94ab9222bbd279b2ac150ed4b5e606820b1d223de08a782724788f","target":"graph","created_at":"2026-07-05T03:55:23Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1906.10462/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Gang Pan, Gang Zheng, Jianhang Huang, Jun Wen, Long Yang, Pengfei Li, Qian Zheng, Yu Zhang","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-25T11:36:18Z","title":"Policy Optimization with Stochastic Mirror Descent"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.10462","kind":"arxiv","version":5},"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":"sha256:3a371c86a0089239ec049d65fc281d77e3a14f4468ba48619161b0e6a15c7782","target":"record","created_at":"2026-07-05T03:55:23Z","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":"f875aaeaf08c4562916aaa942b2c117733147965772141e1959bf148159226f8","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-25T11:36:18Z","title_canon_sha256":"de562ce0dff637a117dbfda371979beacd3c3fbc525ddf3c650af9045c5e5ed7"},"schema_version":"1.0","source":{"id":"1906.10462","kind":"arxiv","version":5}},"canonical_sha256":"ba8f553367446f2673c09268336f5e457d222397d107f1d1b06f5b9eceb94fb2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ba8f553367446f2673c09268336f5e457d222397d107f1d1b06f5b9eceb94fb2","first_computed_at":"2026-07-05T03:55:23.982719Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:55:23.982719Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"u0iWgY0HIyZSExJgM01iTe9WjY+rr1qtvseFgoA1VvbTJnXhGY06oytnTUWjWvAlkAgvW+/wpmZusljr0afsDw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:55:23.983182Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.10462","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3a371c86a0089239ec049d65fc281d77e3a14f4468ba48619161b0e6a15c7782","sha256:a1c66ce99c94ab9222bbd279b2ac150ed4b5e606820b1d223de08a782724788f"],"state_sha256":"e44db5f54fad19866c9adcabf1330edb98695f916c94bc6afa8d663cd2a105ca"}