{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:XOL2LJJGEBBPK2SOHWRYCLFCXO","short_pith_number":"pith:XOL2LJJG","canonical_record":{"source":{"id":"1710.11198","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-10-30T19:03:48Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"946ce72f2c221088eada235d09cd81f77704a4b0b6f2646461d4acf2610cd516","abstract_canon_sha256":"3b962693a1ac72648e97d889d124f761202b84ddbcb10f9fd9c420a83007a1bb"},"schema_version":"1.0"},"canonical_sha256":"bb97a5a5262042f56a4e3da3812ca2bb85b8f426fa77462c4aeabb711a5050ad","source":{"kind":"arxiv","id":"1710.11198","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.11198","created_at":"2026-05-18T00:22:44Z"},{"alias_kind":"arxiv_version","alias_value":"1710.11198v4","created_at":"2026-05-18T00:22:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.11198","created_at":"2026-05-18T00:22:44Z"},{"alias_kind":"pith_short_12","alias_value":"XOL2LJJGEBBP","created_at":"2026-05-18T12:31:56Z"},{"alias_kind":"pith_short_16","alias_value":"XOL2LJJGEBBPK2SO","created_at":"2026-05-18T12:31:56Z"},{"alias_kind":"pith_short_8","alias_value":"XOL2LJJG","created_at":"2026-05-18T12:31:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:XOL2LJJGEBBPK2SOHWRYCLFCXO","target":"record","payload":{"canonical_record":{"source":{"id":"1710.11198","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-10-30T19:03:48Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"946ce72f2c221088eada235d09cd81f77704a4b0b6f2646461d4acf2610cd516","abstract_canon_sha256":"3b962693a1ac72648e97d889d124f761202b84ddbcb10f9fd9c420a83007a1bb"},"schema_version":"1.0"},"canonical_sha256":"bb97a5a5262042f56a4e3da3812ca2bb85b8f426fa77462c4aeabb711a5050ad","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:44.425919Z","signature_b64":"ax8bB9Vj2OoG1Yi6S7JgYPHpT3z9/sHA8VrGFwj8CuUQr0duqx+m/yfntRd79PVyF4VUE6lXq5qGkdQ/B7wbAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb97a5a5262042f56a4e3da3812ca2bb85b8f426fa77462c4aeabb711a5050ad","last_reissued_at":"2026-05-18T00:22:44.425481Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:44.425481Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1710.11198","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":"2026-05-18T00:22:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U10d5PbNFzfJkYcQWGJkXO68US2Cg7xMqveCu5qDSFBPzz0zg6JnLUO5t+V6NSHOM/Mnp8jGvO7JyN0Az3EnCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T09:56:20.134390Z"},"content_sha256":"710da78aaf0abfff04191eecab8dc04c5a22388593cbd7e3f6d3b4a8b245626a","schema_version":"1.0","event_id":"sha256:710da78aaf0abfff04191eecab8dc04c5a22388593cbd7e3f6d3b4a8b245626a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:XOL2LJJGEBBPK2SOHWRYCLFCXO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Action-depedent Control Variates for Policy Optimization via Stein's Identity","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Dengyong Zhou, Hao Liu, Jian Peng, Qiang Liu, Yihao Feng, Yi Mao","submitted_at":"2017-10-30T19:03:48Z","abstract_excerpt":"Policy gradient methods have achieved remarkable successes in solving challenging reinforcement learning problems. However, it still often suffers from the large variance issue on policy gradient estimation, which leads to poor sample efficiency during training. In this work, we propose a control variate method to effectively reduce variance for policy gradient methods. Motivated by the Stein's identity, our method extends the previous control variate methods used in REINFORCE and advantage actor-critic by introducing more general action-dependent baseline functions. Empirical studies show tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.11198","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":"2026-05-18T00:22:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aB0Eew7ZXEVFkrhNF4G8mwApGlNObU4Vq0kl1ldM9X80oWlXBleCOsWyooYZWUHukqRASizuG6+mrqIqjcNSAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T09:56:20.134757Z"},"content_sha256":"9bf34ac523b0e4c61cd488cad4448a9ccdde11bfc63e87964821ac838ed01078","schema_version":"1.0","event_id":"sha256:9bf34ac523b0e4c61cd488cad4448a9ccdde11bfc63e87964821ac838ed01078"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XOL2LJJGEBBPK2SOHWRYCLFCXO/bundle.json","state_url":"https://pith.science/pith/XOL2LJJGEBBPK2SOHWRYCLFCXO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XOL2LJJGEBBPK2SOHWRYCLFCXO/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":"2026-05-20T09:56:20Z","links":{"resolver":"https://pith.science/pith/XOL2LJJGEBBPK2SOHWRYCLFCXO","bundle":"https://pith.science/pith/XOL2LJJGEBBPK2SOHWRYCLFCXO/bundle.json","state":"https://pith.science/pith/XOL2LJJGEBBPK2SOHWRYCLFCXO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XOL2LJJGEBBPK2SOHWRYCLFCXO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:XOL2LJJGEBBPK2SOHWRYCLFCXO","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":"3b962693a1ac72648e97d889d124f761202b84ddbcb10f9fd9c420a83007a1bb","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-10-30T19:03:48Z","title_canon_sha256":"946ce72f2c221088eada235d09cd81f77704a4b0b6f2646461d4acf2610cd516"},"schema_version":"1.0","source":{"id":"1710.11198","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.11198","created_at":"2026-05-18T00:22:44Z"},{"alias_kind":"arxiv_version","alias_value":"1710.11198v4","created_at":"2026-05-18T00:22:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.11198","created_at":"2026-05-18T00:22:44Z"},{"alias_kind":"pith_short_12","alias_value":"XOL2LJJGEBBP","created_at":"2026-05-18T12:31:56Z"},{"alias_kind":"pith_short_16","alias_value":"XOL2LJJGEBBPK2SO","created_at":"2026-05-18T12:31:56Z"},{"alias_kind":"pith_short_8","alias_value":"XOL2LJJG","created_at":"2026-05-18T12:31:56Z"}],"graph_snapshots":[{"event_id":"sha256:9bf34ac523b0e4c61cd488cad4448a9ccdde11bfc63e87964821ac838ed01078","target":"graph","created_at":"2026-05-18T00:22:44Z","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":"Policy gradient methods have achieved remarkable successes in solving challenging reinforcement learning problems. However, it still often suffers from the large variance issue on policy gradient estimation, which leads to poor sample efficiency during training. In this work, we propose a control variate method to effectively reduce variance for policy gradient methods. Motivated by the Stein's identity, our method extends the previous control variate methods used in REINFORCE and advantage actor-critic by introducing more general action-dependent baseline functions. Empirical studies show tha","authors_text":"Dengyong Zhou, Hao Liu, Jian Peng, Qiang Liu, Yihao Feng, Yi Mao","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-10-30T19:03:48Z","title":"Action-depedent Control Variates for Policy Optimization via Stein's Identity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.11198","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":"sha256:710da78aaf0abfff04191eecab8dc04c5a22388593cbd7e3f6d3b4a8b245626a","target":"record","created_at":"2026-05-18T00:22:44Z","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":"3b962693a1ac72648e97d889d124f761202b84ddbcb10f9fd9c420a83007a1bb","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-10-30T19:03:48Z","title_canon_sha256":"946ce72f2c221088eada235d09cd81f77704a4b0b6f2646461d4acf2610cd516"},"schema_version":"1.0","source":{"id":"1710.11198","kind":"arxiv","version":4}},"canonical_sha256":"bb97a5a5262042f56a4e3da3812ca2bb85b8f426fa77462c4aeabb711a5050ad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bb97a5a5262042f56a4e3da3812ca2bb85b8f426fa77462c4aeabb711a5050ad","first_computed_at":"2026-05-18T00:22:44.425481Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:22:44.425481Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ax8bB9Vj2OoG1Yi6S7JgYPHpT3z9/sHA8VrGFwj8CuUQr0duqx+m/yfntRd79PVyF4VUE6lXq5qGkdQ/B7wbAg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:22:44.425919Z","signed_message":"canonical_sha256_bytes"},"source_id":"1710.11198","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:710da78aaf0abfff04191eecab8dc04c5a22388593cbd7e3f6d3b4a8b245626a","sha256:9bf34ac523b0e4c61cd488cad4448a9ccdde11bfc63e87964821ac838ed01078"],"state_sha256":"d76db6f97b48c117c5d4c2b4ef3fd4d942fc4304e04e88505295d89b4316b6a6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DcVeHXBaK/FIp/1sWi/AkBRH9qRmaZqgsc1SBTsymqgudpfcMs1jxjOrX4shSQgkhDWcNc4oovcIoL6MVO6KAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-20T09:56:20.136821Z","bundle_sha256":"bcebc03065e9633f036662e8a35000558b3e48e5c5071f4033ac46d78428520c"}}