{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:FIN5YJADZOS4QZCY4EQPFXCW7W","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":"07b6ecdf80008c2eca0e3fe913cdf1bc9b18f9a89911f50a1d0f9f2643bb0416","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-20T01:30:43Z","title_canon_sha256":"becb9f897a3403f9b5324b46cab49a738110d689afe24c09f59c13349b4caa7e"},"schema_version":"1.0","source":{"id":"2005.09814","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.09814","created_at":"2026-07-05T02:46:40Z"},{"alias_kind":"arxiv_version","alias_value":"2005.09814v5","created_at":"2026-07-05T02:46:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.09814","created_at":"2026-07-05T02:46:40Z"},{"alias_kind":"pith_short_12","alias_value":"FIN5YJADZOS4","created_at":"2026-07-05T02:46:40Z"},{"alias_kind":"pith_short_16","alias_value":"FIN5YJADZOS4QZCY","created_at":"2026-07-05T02:46:40Z"},{"alias_kind":"pith_short_8","alias_value":"FIN5YJAD","created_at":"2026-07-05T02:46:40Z"}],"graph_snapshots":[{"event_id":"sha256:ef2336cdf55333e845ba571fc18f9119ad22b0dd7f508dd8065c05bd6a17f358","target":"graph","created_at":"2026-07-05T02:46:40Z","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/2005.09814/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Mirror descent (MD), a well-known first-order method in constrained convex optimization, has recently been shown as an important tool to analyze trust-region algorithms in reinforcement learning (RL). However, there remains a considerable gap between such theoretically analyzed algorithms and the ones used in practice. Inspired by this, we propose an efficient RL algorithm, called {\\em mirror descent policy optimization} (MDPO). MDPO iteratively updates the policy by {\\em approximately} solving a trust-region problem, whose objective function consists of two terms: a linearization of the stand","authors_text":"Lior Shani, Manan Tomar, Mohammad Ghavamzadeh, Yonathan Efroni","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-20T01:30:43Z","title":"Mirror Descent Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.09814","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:ba3114e833b87b330db46657dab5dabb429beac60a8649a350fdeaca3478670f","target":"record","created_at":"2026-07-05T02:46:40Z","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":"07b6ecdf80008c2eca0e3fe913cdf1bc9b18f9a89911f50a1d0f9f2643bb0416","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-20T01:30:43Z","title_canon_sha256":"becb9f897a3403f9b5324b46cab49a738110d689afe24c09f59c13349b4caa7e"},"schema_version":"1.0","source":{"id":"2005.09814","kind":"arxiv","version":5}},"canonical_sha256":"2a1bdc2403cba5c86458e120f2dc56fdb9d68a996c0cfbc8efab3f81b1cd4721","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2a1bdc2403cba5c86458e120f2dc56fdb9d68a996c0cfbc8efab3f81b1cd4721","first_computed_at":"2026-07-05T02:46:40.750341Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:46:40.750341Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ocLjLIDbc5XRA1Je/NCYnQHmvrR0haCKnEik8bV8pwTNozToqrhitjDeH7kHK5OkQQpsjC52f46nrq3D70SbCA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:46:40.750833Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.09814","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ba3114e833b87b330db46657dab5dabb429beac60a8649a350fdeaca3478670f","sha256:ef2336cdf55333e845ba571fc18f9119ad22b0dd7f508dd8065c05bd6a17f358"],"state_sha256":"38025183909dd8c3bd44062daf2b24e118ffeadacaa2f47a7ce6f1e52df11a5f"}