{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:WXSM7OQYGVYC2SSYNWD4DIQQG2","short_pith_number":"pith:WXSM7OQY","canonical_record":{"source":{"id":"1806.05618","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-14T15:49:13Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"1e6c381cf9831494e63fdda8979a0f0936dfb21630e98a3b3c3d1a65c7a6c8f7","abstract_canon_sha256":"08be26aa83533a36755e0a5c3706c11ae34ee2075d458f5c99bba3ca54dd38a8"},"schema_version":"1.0"},"canonical_sha256":"b5e4cfba1835702d4a586d87c1a21036a09f2c6baea1fe8a21d12034f29436fa","source":{"kind":"arxiv","id":"1806.05618","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.05618","created_at":"2026-05-18T00:13:14Z"},{"alias_kind":"arxiv_version","alias_value":"1806.05618v1","created_at":"2026-05-18T00:13:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.05618","created_at":"2026-05-18T00:13:14Z"},{"alias_kind":"pith_short_12","alias_value":"WXSM7OQYGVYC","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"WXSM7OQYGVYC2SSY","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"WXSM7OQY","created_at":"2026-05-18T12:33:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:WXSM7OQYGVYC2SSYNWD4DIQQG2","target":"record","payload":{"canonical_record":{"source":{"id":"1806.05618","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-14T15:49:13Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"1e6c381cf9831494e63fdda8979a0f0936dfb21630e98a3b3c3d1a65c7a6c8f7","abstract_canon_sha256":"08be26aa83533a36755e0a5c3706c11ae34ee2075d458f5c99bba3ca54dd38a8"},"schema_version":"1.0"},"canonical_sha256":"b5e4cfba1835702d4a586d87c1a21036a09f2c6baea1fe8a21d12034f29436fa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:13:14.583488Z","signature_b64":"5xjHyj1oUkNxNySIBD6EWDBtbPmzPeCJG/JgtBo/ilAD0bB8/2o4huVcR8UyY+XOWQxSrzmdqUrGZ0gUyHrXBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b5e4cfba1835702d4a586d87c1a21036a09f2c6baea1fe8a21d12034f29436fa","last_reissued_at":"2026-05-18T00:13:14.582840Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:13:14.582840Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1806.05618","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":"2026-05-18T00:13:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3iopyfknW8KtrQTH+nlxps5H9myNGGUBr1is/N0Blhf9hQOamQJQ8Bg5DFFkixXR6I40gvHyNuV/3IppGgRpDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T12:17:31.381243Z"},"content_sha256":"513aeb5521fe79a2f31c927a9eb069f322244bd206df7035e68602ece6657d5f","schema_version":"1.0","event_id":"sha256:513aeb5521fe79a2f31c927a9eb069f322244bd206df7035e68602ece6657d5f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:WXSM7OQYGVYC2SSYNWD4DIQQG2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Stochastic Variance-Reduced Policy Gradient","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Damiano Binaghi, Giuseppe Canonaco, Marcello Restelli, Matteo Papini, Matteo Pirotta","submitted_at":"2018-06-14T15:49:13Z","abstract_excerpt":"In this paper, we propose a novel reinforcement- learning algorithm consisting in a stochastic variance-reduced version of policy gradient for solving Markov Decision Processes (MDPs). Stochastic variance-reduced gradient (SVRG) methods have proven to be very successful in supervised learning. However, their adaptation to policy gradient is not straightforward and needs to account for I) a non-concave objective func- tion; II) approximations in the full gradient com- putation; and III) a non-stationary sampling pro- cess. The result is SVRPG, a stochastic variance- reduced policy gradient algo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.05618","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":"2026-05-18T00:13:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KQFVHUg+uXYtrgAi+UuIbMizo8PBukJ0wdWoeiihhcvbeN/burXAYP6lg3qq5BBpQzk8rBoiHa2QPhFSa9fsCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T12:17:31.381875Z"},"content_sha256":"483a8c12424baca15ece7b71a465d49a3abffedf6f193762b5167519d4db5457","schema_version":"1.0","event_id":"sha256:483a8c12424baca15ece7b71a465d49a3abffedf6f193762b5167519d4db5457"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WXSM7OQYGVYC2SSYNWD4DIQQG2/bundle.json","state_url":"https://pith.science/pith/WXSM7OQYGVYC2SSYNWD4DIQQG2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WXSM7OQYGVYC2SSYNWD4DIQQG2/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":"2026-05-26T12:17:31Z","links":{"resolver":"https://pith.science/pith/WXSM7OQYGVYC2SSYNWD4DIQQG2","bundle":"https://pith.science/pith/WXSM7OQYGVYC2SSYNWD4DIQQG2/bundle.json","state":"https://pith.science/pith/WXSM7OQYGVYC2SSYNWD4DIQQG2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WXSM7OQYGVYC2SSYNWD4DIQQG2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:WXSM7OQYGVYC2SSYNWD4DIQQG2","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":"08be26aa83533a36755e0a5c3706c11ae34ee2075d458f5c99bba3ca54dd38a8","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-14T15:49:13Z","title_canon_sha256":"1e6c381cf9831494e63fdda8979a0f0936dfb21630e98a3b3c3d1a65c7a6c8f7"},"schema_version":"1.0","source":{"id":"1806.05618","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.05618","created_at":"2026-05-18T00:13:14Z"},{"alias_kind":"arxiv_version","alias_value":"1806.05618v1","created_at":"2026-05-18T00:13:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.05618","created_at":"2026-05-18T00:13:14Z"},{"alias_kind":"pith_short_12","alias_value":"WXSM7OQYGVYC","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"WXSM7OQYGVYC2SSY","created_at":"2026-05-18T12:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"WXSM7OQY","created_at":"2026-05-18T12:33:01Z"}],"graph_snapshots":[{"event_id":"sha256:483a8c12424baca15ece7b71a465d49a3abffedf6f193762b5167519d4db5457","target":"graph","created_at":"2026-05-18T00:13:14Z","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":"In this paper, we propose a novel reinforcement- learning algorithm consisting in a stochastic variance-reduced version of policy gradient for solving Markov Decision Processes (MDPs). Stochastic variance-reduced gradient (SVRG) methods have proven to be very successful in supervised learning. However, their adaptation to policy gradient is not straightforward and needs to account for I) a non-concave objective func- tion; II) approximations in the full gradient com- putation; and III) a non-stationary sampling pro- cess. The result is SVRPG, a stochastic variance- reduced policy gradient algo","authors_text":"Damiano Binaghi, Giuseppe Canonaco, Marcello Restelli, Matteo Papini, Matteo Pirotta","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-14T15:49:13Z","title":"Stochastic Variance-Reduced Policy Gradient"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.05618","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":"sha256:513aeb5521fe79a2f31c927a9eb069f322244bd206df7035e68602ece6657d5f","target":"record","created_at":"2026-05-18T00:13:14Z","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":"08be26aa83533a36755e0a5c3706c11ae34ee2075d458f5c99bba3ca54dd38a8","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-14T15:49:13Z","title_canon_sha256":"1e6c381cf9831494e63fdda8979a0f0936dfb21630e98a3b3c3d1a65c7a6c8f7"},"schema_version":"1.0","source":{"id":"1806.05618","kind":"arxiv","version":1}},"canonical_sha256":"b5e4cfba1835702d4a586d87c1a21036a09f2c6baea1fe8a21d12034f29436fa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b5e4cfba1835702d4a586d87c1a21036a09f2c6baea1fe8a21d12034f29436fa","first_computed_at":"2026-05-18T00:13:14.582840Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:13:14.582840Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5xjHyj1oUkNxNySIBD6EWDBtbPmzPeCJG/JgtBo/ilAD0bB8/2o4huVcR8UyY+XOWQxSrzmdqUrGZ0gUyHrXBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:13:14.583488Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.05618","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:513aeb5521fe79a2f31c927a9eb069f322244bd206df7035e68602ece6657d5f","sha256:483a8c12424baca15ece7b71a465d49a3abffedf6f193762b5167519d4db5457"],"state_sha256":"9a695a9ae44868c1b298b37a1bbff44e978db811a989fea3319670260499f53e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C009UXMiG6bXY/vuxZY2p3QGR/v9MOQwjxZ7PUWz2HrcYcX/YYuFm8cUjDIpDBa+DUvoTRXI9d/pr8o3gJIhAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T12:17:31.385265Z","bundle_sha256":"21250dfe7c9c85351cd56d138d3818ec6334a748e0b2d7b6eede05346d6adcf2"}}