{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ORMMBOA3ZUNO6OSPI7AMQNVZKP","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":"ed7ba10911db093e686a01df1ec483f9835226bffa6bd63baff45cc3f248fb3b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-21T18:12:39Z","title_canon_sha256":"cb1ad5c2d33a1b2509ed44aa78774dce0a6ffd97a0031ecf69a212d18d791c0e"},"schema_version":"1.0","source":{"id":"2405.13136","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.13136","created_at":"2026-07-05T09:13:02Z"},{"alias_kind":"arxiv_version","alias_value":"2405.13136v3","created_at":"2026-07-05T09:13:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.13136","created_at":"2026-07-05T09:13:02Z"},{"alias_kind":"pith_short_12","alias_value":"ORMMBOA3ZUNO","created_at":"2026-07-05T09:13:02Z"},{"alias_kind":"pith_short_16","alias_value":"ORMMBOA3ZUNO6OSP","created_at":"2026-07-05T09:13:02Z"},{"alias_kind":"pith_short_8","alias_value":"ORMMBOA3","created_at":"2026-07-05T09:13:02Z"}],"graph_snapshots":[{"event_id":"sha256:3928848302a3ee622256ffe04d5ceae2d4ef2dca98e8882a2b02ea78166232cc","target":"graph","created_at":"2026-07-05T09:13:02Z","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/2405.13136/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider (stochastic) softmax policy gradient (PG) methods for bandits and tabular Markov decision processes (MDPs). While the PG objective is non-concave, recent research has used the objective's smoothness and gradient domination properties to achieve convergence to an optimal policy. However, these theoretical results require setting the algorithm parameters according to unknown problem-dependent quantities (e.g. the optimal action or the true reward vector in a bandit problem). To address this issue, we borrow ideas from the optimization literature to design practical, principled PG met","authors_text":"Anant Raj, Matin Aghaei, Michael Lu, Sharan Vaswani","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-21T18:12:39Z","title":"Towards Principled, Practical Policy Gradient for Bandits and Tabular MDPs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.13136","kind":"arxiv","version":3},"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":"sha256:4f289bd809d1824095af777f863dddeeee27a5d4f1b90d470a5d152639230681","target":"record","created_at":"2026-07-05T09:13:02Z","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":"ed7ba10911db093e686a01df1ec483f9835226bffa6bd63baff45cc3f248fb3b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-21T18:12:39Z","title_canon_sha256":"cb1ad5c2d33a1b2509ed44aa78774dce0a6ffd97a0031ecf69a212d18d791c0e"},"schema_version":"1.0","source":{"id":"2405.13136","kind":"arxiv","version":3}},"canonical_sha256":"7458c0b81bcd1aef3a4f47c0c836b953f87dd435ae502608cd6be008d41937c3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7458c0b81bcd1aef3a4f47c0c836b953f87dd435ae502608cd6be008d41937c3","first_computed_at":"2026-07-05T09:13:02.887782Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:13:02.887782Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RNfxOIxDzi1e0fWpoqTNXsqDutWtFP+R2jqgir65DHBBjlag1m7KTXKjsQ93p800K1GvlfB4HfVKsSp9AKIdBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:13:02.888271Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.13136","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4f289bd809d1824095af777f863dddeeee27a5d4f1b90d470a5d152639230681","sha256:3928848302a3ee622256ffe04d5ceae2d4ef2dca98e8882a2b02ea78166232cc"],"state_sha256":"87ccb2405d0631dec66cc101fcbab5f1c764db887c36096fd2cb0a9527d8296a"}