{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:INKTMVWYD5CFHEGDGKCMYQYPKZ","short_pith_number":"pith:INKTMVWY","canonical_record":{"source":{"id":"1710.06034","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-10-17T00:05:06Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"93482897e2129506c84302af8dd457e7f3684f595d177da501adb09e4a45581c","abstract_canon_sha256":"a24d904831dbf4361ce8b56cc0d774bbb4ead20725e54fea4b95aac593582253"},"schema_version":"1.0"},"canonical_sha256":"43553656d81f445390c33284cc430f566c2198106142a23702ceaea4384e44d7","source":{"kind":"arxiv","id":"1710.06034","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.06034","created_at":"2026-05-18T00:19:49Z"},{"alias_kind":"arxiv_version","alias_value":"1710.06034v4","created_at":"2026-05-18T00:19:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.06034","created_at":"2026-05-18T00:19:49Z"},{"alias_kind":"pith_short_12","alias_value":"INKTMVWYD5CF","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_16","alias_value":"INKTMVWYD5CFHEGD","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_8","alias_value":"INKTMVWY","created_at":"2026-05-18T12:31:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:INKTMVWYD5CFHEGDGKCMYQYPKZ","target":"record","payload":{"canonical_record":{"source":{"id":"1710.06034","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-10-17T00:05:06Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"93482897e2129506c84302af8dd457e7f3684f595d177da501adb09e4a45581c","abstract_canon_sha256":"a24d904831dbf4361ce8b56cc0d774bbb4ead20725e54fea4b95aac593582253"},"schema_version":"1.0"},"canonical_sha256":"43553656d81f445390c33284cc430f566c2198106142a23702ceaea4384e44d7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:19:49.092569Z","signature_b64":"BNH1mzspGHeWDI/Ffeq6LLALp1szKA6ZXNJVIUU7u56sD3aBvOFMao2nXOJHPj9+ZN8UbcNEpFRJcYnglJucBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"43553656d81f445390c33284cc430f566c2198106142a23702ceaea4384e44d7","last_reissued_at":"2026-05-18T00:19:49.091855Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:19:49.091855Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1710.06034","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:19:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CXcSg88dUC+hMy9ckg32W5JlNFbsCwPZVP65dAWuG6th5NbtCSYfzJtjzIhaUWnj/QHRKS4kT8KpC+tTZkA9CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T02:45:38.064625Z"},"content_sha256":"6accd8d6c10fab78c6f2b21a86fba004300d693a9534c06ac0f459b307b5d11e","schema_version":"1.0","event_id":"sha256:6accd8d6c10fab78c6f2b21a86fba004300d693a9534c06ac0f459b307b5d11e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:INKTMVWYD5CFHEGDGKCMYQYPKZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Stochastic Variance Reduction for Policy Gradient Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jian Peng, Qiang Liu, Tianbing Xu","submitted_at":"2017-10-17T00:05:06Z","abstract_excerpt":"Recent advances in policy gradient methods and deep learning have demonstrated their applicability for complex reinforcement learning problems. However, the variance of the performance gradient estimates obtained from the simulation is often excessive, leading to poor sample efficiency. In this paper, we apply the stochastic variance reduced gradient descent (SVRG) to model-free policy gradient to significantly improve the sample-efficiency. The SVRG estimation is incorporated into a trust-region Newton conjugate gradient framework for the policy optimization. On several Mujoco tasks, our meth"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.06034","kind":"arxiv","version":4},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:19:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Fgw2PyYLBUnct0U77i7YmLPCbcK6XMIYQV7HR1YSHpuhc0dCCEscwIWnIOBUFwW9Eb02akDxqeNYxrP2Ih7/Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T02:45:38.064994Z"},"content_sha256":"3eda674db7fa12443ca3c565c45694ae105d266b3deae2132b39e94de4dc0e2d","schema_version":"1.0","event_id":"sha256:3eda674db7fa12443ca3c565c45694ae105d266b3deae2132b39e94de4dc0e2d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/INKTMVWYD5CFHEGDGKCMYQYPKZ/bundle.json","state_url":"https://pith.science/pith/INKTMVWYD5CFHEGDGKCMYQYPKZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/INKTMVWYD5CFHEGDGKCMYQYPKZ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-30T02:45:38Z","links":{"resolver":"https://pith.science/pith/INKTMVWYD5CFHEGDGKCMYQYPKZ","bundle":"https://pith.science/pith/INKTMVWYD5CFHEGDGKCMYQYPKZ/bundle.json","state":"https://pith.science/pith/INKTMVWYD5CFHEGDGKCMYQYPKZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/INKTMVWYD5CFHEGDGKCMYQYPKZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:INKTMVWYD5CFHEGDGKCMYQYPKZ","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":"a24d904831dbf4361ce8b56cc0d774bbb4ead20725e54fea4b95aac593582253","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-10-17T00:05:06Z","title_canon_sha256":"93482897e2129506c84302af8dd457e7f3684f595d177da501adb09e4a45581c"},"schema_version":"1.0","source":{"id":"1710.06034","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.06034","created_at":"2026-05-18T00:19:49Z"},{"alias_kind":"arxiv_version","alias_value":"1710.06034v4","created_at":"2026-05-18T00:19:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.06034","created_at":"2026-05-18T00:19:49Z"},{"alias_kind":"pith_short_12","alias_value":"INKTMVWYD5CF","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_16","alias_value":"INKTMVWYD5CFHEGD","created_at":"2026-05-18T12:31:21Z"},{"alias_kind":"pith_short_8","alias_value":"INKTMVWY","created_at":"2026-05-18T12:31:21Z"}],"graph_snapshots":[{"event_id":"sha256:3eda674db7fa12443ca3c565c45694ae105d266b3deae2132b39e94de4dc0e2d","target":"graph","created_at":"2026-05-18T00:19:49Z","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":"Recent advances in policy gradient methods and deep learning have demonstrated their applicability for complex reinforcement learning problems. However, the variance of the performance gradient estimates obtained from the simulation is often excessive, leading to poor sample efficiency. In this paper, we apply the stochastic variance reduced gradient descent (SVRG) to model-free policy gradient to significantly improve the sample-efficiency. The SVRG estimation is incorporated into a trust-region Newton conjugate gradient framework for the policy optimization. On several Mujoco tasks, our meth","authors_text":"Jian Peng, Qiang Liu, Tianbing Xu","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-10-17T00:05:06Z","title":"Stochastic Variance Reduction for Policy Gradient Estimation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.06034","kind":"arxiv","version":4},"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":"sha256:6accd8d6c10fab78c6f2b21a86fba004300d693a9534c06ac0f459b307b5d11e","target":"record","created_at":"2026-05-18T00:19:49Z","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":"a24d904831dbf4361ce8b56cc0d774bbb4ead20725e54fea4b95aac593582253","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-10-17T00:05:06Z","title_canon_sha256":"93482897e2129506c84302af8dd457e7f3684f595d177da501adb09e4a45581c"},"schema_version":"1.0","source":{"id":"1710.06034","kind":"arxiv","version":4}},"canonical_sha256":"43553656d81f445390c33284cc430f566c2198106142a23702ceaea4384e44d7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"43553656d81f445390c33284cc430f566c2198106142a23702ceaea4384e44d7","first_computed_at":"2026-05-18T00:19:49.091855Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:19:49.091855Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BNH1mzspGHeWDI/Ffeq6LLALp1szKA6ZXNJVIUU7u56sD3aBvOFMao2nXOJHPj9+ZN8UbcNEpFRJcYnglJucBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:19:49.092569Z","signed_message":"canonical_sha256_bytes"},"source_id":"1710.06034","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6accd8d6c10fab78c6f2b21a86fba004300d693a9534c06ac0f459b307b5d11e","sha256:3eda674db7fa12443ca3c565c45694ae105d266b3deae2132b39e94de4dc0e2d"],"state_sha256":"538030e20215e1b8ac3d1912bd0497e556d5e513bcc7e9b7afa6d84f8dc054ea"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fOXWrxJc0JbowtvxCCF1I/BU2TW+Vn5eQcKL8dV1JcHIEeNvw+HXRhyV8mnnVdS9d9zZ9nTowgacTjF4SYkACA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T02:45:38.067149Z","bundle_sha256":"8a251d2c61d0593ab9909b456097291eb181eea1cb3d614d5733edfb37723be4"}}