{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:NJXHTWGEVOWI6WQAG3P5E5KA5O","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":"9c436a50f1de1ae4a3e4284b32e33bd1e40533eef59e08a65b79aca486d11043","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-18T11:33:22Z","title_canon_sha256":"328fb181070d751d409e800b6c412868ba1e42b2a787dc8b14351c11d659e4bd"},"schema_version":"1.0","source":{"id":"2310.11897","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.11897","created_at":"2026-07-05T08:28:03Z"},{"alias_kind":"arxiv_version","alias_value":"2310.11897v3","created_at":"2026-07-05T08:28:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.11897","created_at":"2026-07-05T08:28:03Z"},{"alias_kind":"pith_short_12","alias_value":"NJXHTWGEVOWI","created_at":"2026-07-05T08:28:03Z"},{"alias_kind":"pith_short_16","alias_value":"NJXHTWGEVOWI6WQA","created_at":"2026-07-05T08:28:03Z"},{"alias_kind":"pith_short_8","alias_value":"NJXHTWGE","created_at":"2026-07-05T08:28:03Z"}],"graph_snapshots":[{"event_id":"sha256:c9a6ca8471825c2f8a79751a58e172daa934b52e03e133a09292a7ff231e25d7","target":"graph","created_at":"2026-07-05T08:28:03Z","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/2310.11897/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Various acceleration approaches for Policy Gradient (PG) have been analyzed within the realm of Reinforcement Learning (RL). However, the theoretical understanding of the widely used momentum-based acceleration method on PG remains largely open. In response to this gap, we adapt the celebrated Nesterov's accelerated gradient (NAG) method to policy optimization in RL, termed \\textit{Accelerated Policy Gradient} (APG). To demonstrate the potential of APG in achieving fast convergence, we formally prove that with the true gradient and under the softmax policy parametrization, APG converges to an ","authors_text":"Ching-pei Lee, Nai-Chieh Huang, Ping-Chun Hsieh, Yen-Ju Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-18T11:33:22Z","title":"Accelerated Policy Gradient: On the Convergence Rates of the Nesterov Momentum for Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.11897","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:db5ad494c8efe9923526a85debdea592d474510c2c6892dbf867a1701b3b758b","target":"record","created_at":"2026-07-05T08:28:03Z","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":"9c436a50f1de1ae4a3e4284b32e33bd1e40533eef59e08a65b79aca486d11043","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-18T11:33:22Z","title_canon_sha256":"328fb181070d751d409e800b6c412868ba1e42b2a787dc8b14351c11d659e4bd"},"schema_version":"1.0","source":{"id":"2310.11897","kind":"arxiv","version":3}},"canonical_sha256":"6a6e79d8c4abac8f5a0036dfd27540eba172735d88f88c1094a0d20150c108eb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6a6e79d8c4abac8f5a0036dfd27540eba172735d88f88c1094a0d20150c108eb","first_computed_at":"2026-07-05T08:28:03.234673Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:28:03.234673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gdViUvgMVIFmPlOCt/zXoaDJwjvrhRYJp9sZ/VCNCh/lGblw8e73IcE+W6q/FYjioBQ9WlNwVhsKANgFNXuNDA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:28:03.235110Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.11897","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:db5ad494c8efe9923526a85debdea592d474510c2c6892dbf867a1701b3b758b","sha256:c9a6ca8471825c2f8a79751a58e172daa934b52e03e133a09292a7ff231e25d7"],"state_sha256":"44dffaa38df2e45537bed26cb86e54a6dbf4e8f8aba160e27a30002e56afe4f4"}