{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:KJUYHCJ2RUWYIZSEGTVMYELRGG","short_pith_number":"pith:KJUYHCJ2","canonical_record":{"source":{"id":"1905.08152","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-20T14:56:22Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"e4355bed9c610271d7553db1918cae3cfed2028961173d9bfc3845fe524498f3","abstract_canon_sha256":"966bfe396aa1cf3dc82c097fe5b6e24b0ea7d0acc8bddefecf7ad544af6b9377"},"schema_version":"1.0"},"canonical_sha256":"526983893a8d2d84664434eacc117131a8bf59c1516d0707aed700117d6a2713","source":{"kind":"arxiv","id":"1905.08152","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.08152","created_at":"2026-05-17T23:45:47Z"},{"alias_kind":"arxiv_version","alias_value":"1905.08152v1","created_at":"2026-05-17T23:45:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.08152","created_at":"2026-05-17T23:45:47Z"},{"alias_kind":"pith_short_12","alias_value":"KJUYHCJ2RUWY","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"KJUYHCJ2RUWYIZSE","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"KJUYHCJ2","created_at":"2026-05-18T12:33:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:KJUYHCJ2RUWYIZSEGTVMYELRGG","target":"record","payload":{"canonical_record":{"source":{"id":"1905.08152","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-20T14:56:22Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"e4355bed9c610271d7553db1918cae3cfed2028961173d9bfc3845fe524498f3","abstract_canon_sha256":"966bfe396aa1cf3dc82c097fe5b6e24b0ea7d0acc8bddefecf7ad544af6b9377"},"schema_version":"1.0"},"canonical_sha256":"526983893a8d2d84664434eacc117131a8bf59c1516d0707aed700117d6a2713","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:47.441165Z","signature_b64":"zxHh9i1e/wg9r7SirJpitC4NVZX5zTCec65XfRRDJSSm07Bs0EreZSQkCrj2TW+vabZZYBItHtWzeeQidPqMAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"526983893a8d2d84664434eacc117131a8bf59c1516d0707aed700117d6a2713","last_reissued_at":"2026-05-17T23:45:47.440459Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:47.440459Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.08152","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:45:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iXq2IJ08TEiXjJYBBVH13TSnaFhqa2WTwVHlvtNtkueN21PNNHJOVIPbCGXwvhHzTUf6DSFmfwftexKL1TKyCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T06:17:39.489993Z"},"content_sha256":"20fe2ee71376a518def2e4d49b4f795f8566e0d6699caa9945ebd1b7af347d0d","schema_version":"1.0","event_id":"sha256:20fe2ee71376a518def2e4d49b4f795f8566e0d6699caa9945ebd1b7af347d0d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:KJUYHCJ2RUWYIZSEGTVMYELRGG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Stochastic Variance Reduction for Deep Q-learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jian Peng, Wei-Ye Zhao, Xiaoming Zhao, Xi-Ya Guan, Yang Liu","submitted_at":"2019-05-20T14:56:22Z","abstract_excerpt":"Recent advances in deep reinforcement learning have achieved human-level performance on a variety of real-world applications. However, the current algorithms still suffer from poor gradient estimation with excessive variance, resulting in unstable training and poor sample efficiency. In our paper, we proposed an innovative optimization strategy by utilizing stochastic variance reduced gradient (SVRG) techniques. With extensive experiments on Atari domain, our method outperforms the deep q-learning baselines on 18 out of 20 games."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.08152","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:45:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ei/slF14C1B/sRmc/3/EwoU435Z+0qwVFTY9mbIRZtR1YPUNb52t3mQsaHxKMVKFmYz9fuJojXA+VHck7PYRCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T06:17:39.490561Z"},"content_sha256":"baea68aa90af6287d8a321c1519003db65e008a81eb5d3df05ac7ca0d84789d0","schema_version":"1.0","event_id":"sha256:baea68aa90af6287d8a321c1519003db65e008a81eb5d3df05ac7ca0d84789d0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KJUYHCJ2RUWYIZSEGTVMYELRGG/bundle.json","state_url":"https://pith.science/pith/KJUYHCJ2RUWYIZSEGTVMYELRGG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KJUYHCJ2RUWYIZSEGTVMYELRGG/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":"2026-06-07T06:17:39Z","links":{"resolver":"https://pith.science/pith/KJUYHCJ2RUWYIZSEGTVMYELRGG","bundle":"https://pith.science/pith/KJUYHCJ2RUWYIZSEGTVMYELRGG/bundle.json","state":"https://pith.science/pith/KJUYHCJ2RUWYIZSEGTVMYELRGG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KJUYHCJ2RUWYIZSEGTVMYELRGG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:KJUYHCJ2RUWYIZSEGTVMYELRGG","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":"966bfe396aa1cf3dc82c097fe5b6e24b0ea7d0acc8bddefecf7ad544af6b9377","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-20T14:56:22Z","title_canon_sha256":"e4355bed9c610271d7553db1918cae3cfed2028961173d9bfc3845fe524498f3"},"schema_version":"1.0","source":{"id":"1905.08152","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.08152","created_at":"2026-05-17T23:45:47Z"},{"alias_kind":"arxiv_version","alias_value":"1905.08152v1","created_at":"2026-05-17T23:45:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.08152","created_at":"2026-05-17T23:45:47Z"},{"alias_kind":"pith_short_12","alias_value":"KJUYHCJ2RUWY","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"KJUYHCJ2RUWYIZSE","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"KJUYHCJ2","created_at":"2026-05-18T12:33:21Z"}],"graph_snapshots":[{"event_id":"sha256:baea68aa90af6287d8a321c1519003db65e008a81eb5d3df05ac7ca0d84789d0","target":"graph","created_at":"2026-05-17T23:45:47Z","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 deep reinforcement learning have achieved human-level performance on a variety of real-world applications. However, the current algorithms still suffer from poor gradient estimation with excessive variance, resulting in unstable training and poor sample efficiency. In our paper, we proposed an innovative optimization strategy by utilizing stochastic variance reduced gradient (SVRG) techniques. With extensive experiments on Atari domain, our method outperforms the deep q-learning baselines on 18 out of 20 games.","authors_text":"Jian Peng, Wei-Ye Zhao, Xiaoming Zhao, Xi-Ya Guan, Yang Liu","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-20T14:56:22Z","title":"Stochastic Variance Reduction for Deep Q-learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.08152","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":"sha256:20fe2ee71376a518def2e4d49b4f795f8566e0d6699caa9945ebd1b7af347d0d","target":"record","created_at":"2026-05-17T23:45:47Z","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":"966bfe396aa1cf3dc82c097fe5b6e24b0ea7d0acc8bddefecf7ad544af6b9377","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-20T14:56:22Z","title_canon_sha256":"e4355bed9c610271d7553db1918cae3cfed2028961173d9bfc3845fe524498f3"},"schema_version":"1.0","source":{"id":"1905.08152","kind":"arxiv","version":1}},"canonical_sha256":"526983893a8d2d84664434eacc117131a8bf59c1516d0707aed700117d6a2713","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"526983893a8d2d84664434eacc117131a8bf59c1516d0707aed700117d6a2713","first_computed_at":"2026-05-17T23:45:47.440459Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:45:47.440459Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zxHh9i1e/wg9r7SirJpitC4NVZX5zTCec65XfRRDJSSm07Bs0EreZSQkCrj2TW+vabZZYBItHtWzeeQidPqMAQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:45:47.441165Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.08152","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:20fe2ee71376a518def2e4d49b4f795f8566e0d6699caa9945ebd1b7af347d0d","sha256:baea68aa90af6287d8a321c1519003db65e008a81eb5d3df05ac7ca0d84789d0"],"state_sha256":"16f508ca30302d20c07c280fd6d86ae876d75888add76cef0adff0f0ddb75fa9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RReczYwKWCLmULmsS6asSaRQ6gUGmjzksRQBR6Ztodm6ALSDqU95l3pzyvipBhPSSrEfPIWj0iZmS8oNyQU/Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T06:17:39.493576Z","bundle_sha256":"44b871018d0ee64340a192c197b92ef1d7b2ac41f912dc278b5c6bde0d8bd291"}}