{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2013:QZOBE7J7HSFUWTF6UFRRY3YFVK","short_pith_number":"pith:QZOBE7J7","schema_version":"1.0","canonical_sha256":"865c127d3f3c8b4b4cbea1631c6f05aab2074562070307caa0a1e6cee0719cb6","source":{"kind":"arxiv","id":"1301.3966","version":1},"attestation_state":"computed","paper":{"title":"Efficient Sample Reuse in Policy Gradients with Parameter-based Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Hirotaka Hachiya, Jun Morimoto, Masashi Sugiyama, Tingting Zhao, Voot Tangkaratt","submitted_at":"2013-01-17T02:15:49Z","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 "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1301.3966","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-01-17T02:15:49Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"9fb3d59465ae94a6e0a0172d9e383f42b9bbc48b723e65f0b811592efd1aa34d","abstract_canon_sha256":"a4230f976b81cbfdb9e59afcbfcaf417e0c97e4e551cc7bb7632d381f31d5a71"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:36:14.754494Z","signature_b64":"JDv+oj8M5o8xpc2lD1qzwW/k4SJBtpHL826aqIZhzYxwxdCy5eYuafoSb84G/+wfmJJfeE4BSKOBtELL/0QaAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"865c127d3f3c8b4b4cbea1631c6f05aab2074562070307caa0a1e6cee0719cb6","last_reissued_at":"2026-05-18T03:36:14.753849Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:36:14.753849Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Sample Reuse in Policy Gradients with Parameter-based Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Hirotaka Hachiya, Jun Morimoto, Masashi Sugiyama, Tingting Zhao, Voot Tangkaratt","submitted_at":"2013-01-17T02:15:49Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1301.3966","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1301.3966","created_at":"2026-05-18T03:36:14.753943+00:00"},{"alias_kind":"arxiv_version","alias_value":"1301.3966v1","created_at":"2026-05-18T03:36:14.753943+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1301.3966","created_at":"2026-05-18T03:36:14.753943+00:00"},{"alias_kind":"pith_short_12","alias_value":"QZOBE7J7HSFU","created_at":"2026-05-18T12:27:57.521954+00:00"},{"alias_kind":"pith_short_16","alias_value":"QZOBE7J7HSFUWTF6","created_at":"2026-05-18T12:27:57.521954+00:00"},{"alias_kind":"pith_short_8","alias_value":"QZOBE7J7","created_at":"2026-05-18T12:27:57.521954+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QZOBE7J7HSFUWTF6UFRRY3YFVK","json":"https://pith.science/pith/QZOBE7J7HSFUWTF6UFRRY3YFVK.json","graph_json":"https://pith.science/api/pith-number/QZOBE7J7HSFUWTF6UFRRY3YFVK/graph.json","events_json":"https://pith.science/api/pith-number/QZOBE7J7HSFUWTF6UFRRY3YFVK/events.json","paper":"https://pith.science/paper/QZOBE7J7"},"agent_actions":{"view_html":"https://pith.science/pith/QZOBE7J7HSFUWTF6UFRRY3YFVK","download_json":"https://pith.science/pith/QZOBE7J7HSFUWTF6UFRRY3YFVK.json","view_paper":"https://pith.science/paper/QZOBE7J7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1301.3966&json=true","fetch_graph":"https://pith.science/api/pith-number/QZOBE7J7HSFUWTF6UFRRY3YFVK/graph.json","fetch_events":"https://pith.science/api/pith-number/QZOBE7J7HSFUWTF6UFRRY3YFVK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QZOBE7J7HSFUWTF6UFRRY3YFVK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QZOBE7J7HSFUWTF6UFRRY3YFVK/action/storage_attestation","attest_author":"https://pith.science/pith/QZOBE7J7HSFUWTF6UFRRY3YFVK/action/author_attestation","sign_citation":"https://pith.science/pith/QZOBE7J7HSFUWTF6UFRRY3YFVK/action/citation_signature","submit_replication":"https://pith.science/pith/QZOBE7J7HSFUWTF6UFRRY3YFVK/action/replication_record"}},"created_at":"2026-05-18T03:36:14.753943+00:00","updated_at":"2026-05-18T03:36:14.753943+00:00"}