{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2013:QZOBE7J7HSFUWTF6UFRRY3YFVK","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":"a4230f976b81cbfdb9e59afcbfcaf417e0c97e4e551cc7bb7632d381f31d5a71","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-01-17T02:15:49Z","title_canon_sha256":"9fb3d59465ae94a6e0a0172d9e383f42b9bbc48b723e65f0b811592efd1aa34d"},"schema_version":"1.0","source":{"id":"1301.3966","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1301.3966","created_at":"2026-05-18T03:36:14Z"},{"alias_kind":"arxiv_version","alias_value":"1301.3966v1","created_at":"2026-05-18T03:36:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1301.3966","created_at":"2026-05-18T03:36:14Z"},{"alias_kind":"pith_short_12","alias_value":"QZOBE7J7HSFU","created_at":"2026-05-18T12:27:57Z"},{"alias_kind":"pith_short_16","alias_value":"QZOBE7J7HSFUWTF6","created_at":"2026-05-18T12:27:57Z"},{"alias_kind":"pith_short_8","alias_value":"QZOBE7J7","created_at":"2026-05-18T12:27:57Z"}],"graph_snapshots":[{"event_id":"sha256:ec2ba41f06d771052e1761b967c5dee59cfb72ff229e5ce88453fb2753a01d55","target":"graph","created_at":"2026-05-18T03:36:14Z","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"},"paper":{"abstract_excerpt":"The policy gradient approach is a flexible and powerful reinforcement learning method particularly for problems with continuous actions such as robot control. A common challenge in this scenario is how to reduce the variance of policy gradient estimates for reliable policy updates. In this paper, we combine the following three ideas and give a highly effective policy gradient method: (a) the policy gradients with parameter based exploration, which is a recently proposed policy search method with low variance of gradient estimates, (b) an importance sampling technique, which allows us to reuse ","authors_text":"Hirotaka Hachiya, Jun Morimoto, Masashi Sugiyama, Tingting Zhao, Voot Tangkaratt","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-01-17T02:15:49Z","title":"Efficient Sample Reuse in Policy Gradients with Parameter-based Exploration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1301.3966","kind":"arxiv","version":1},"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":"sha256:3cc46f99f61677a6fb0023337111a059468f8e284a575a86045e631d5c87f791","target":"record","created_at":"2026-05-18T03:36:14Z","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":"a4230f976b81cbfdb9e59afcbfcaf417e0c97e4e551cc7bb7632d381f31d5a71","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-01-17T02:15:49Z","title_canon_sha256":"9fb3d59465ae94a6e0a0172d9e383f42b9bbc48b723e65f0b811592efd1aa34d"},"schema_version":"1.0","source":{"id":"1301.3966","kind":"arxiv","version":1}},"canonical_sha256":"865c127d3f3c8b4b4cbea1631c6f05aab2074562070307caa0a1e6cee0719cb6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"865c127d3f3c8b4b4cbea1631c6f05aab2074562070307caa0a1e6cee0719cb6","first_computed_at":"2026-05-18T03:36:14.753849Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:36:14.753849Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JDv+oj8M5o8xpc2lD1qzwW/k4SJBtpHL826aqIZhzYxwxdCy5eYuafoSb84G/+wfmJJfeE4BSKOBtELL/0QaAg==","signature_status":"signed_v1","signed_at":"2026-05-18T03:36:14.754494Z","signed_message":"canonical_sha256_bytes"},"source_id":"1301.3966","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3cc46f99f61677a6fb0023337111a059468f8e284a575a86045e631d5c87f791","sha256:ec2ba41f06d771052e1761b967c5dee59cfb72ff229e5ce88453fb2753a01d55"],"state_sha256":"84b1167c01541816c453583cf247fdca69798750ffb6fde037284f7d26f72186"}