{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:WXSM7OQYGVYC2SSYNWD4DIQQG2","short_pith_number":"pith:WXSM7OQY","schema_version":"1.0","canonical_sha256":"b5e4cfba1835702d4a586d87c1a21036a09f2c6baea1fe8a21d12034f29436fa","source":{"kind":"arxiv","id":"1806.05618","version":1},"attestation_state":"computed","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"},"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":"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1806.05618","created_at":"2026-05-18T00:13:14.582934+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.05618v1","created_at":"2026-05-18T00:13:14.582934+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.05618","created_at":"2026-05-18T00:13:14.582934+00:00"},{"alias_kind":"pith_short_12","alias_value":"WXSM7OQYGVYC","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_16","alias_value":"WXSM7OQYGVYC2SSY","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_8","alias_value":"WXSM7OQY","created_at":"2026-05-18T12:33:01.666342+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.16474","citing_title":"Reinforcement Learning-based Control via Y-wise Affine Neural Networks (YANNs)","ref_index":67,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WXSM7OQYGVYC2SSYNWD4DIQQG2","json":"https://pith.science/pith/WXSM7OQYGVYC2SSYNWD4DIQQG2.json","graph_json":"https://pith.science/api/pith-number/WXSM7OQYGVYC2SSYNWD4DIQQG2/graph.json","events_json":"https://pith.science/api/pith-number/WXSM7OQYGVYC2SSYNWD4DIQQG2/events.json","paper":"https://pith.science/paper/WXSM7OQY"},"agent_actions":{"view_html":"https://pith.science/pith/WXSM7OQYGVYC2SSYNWD4DIQQG2","download_json":"https://pith.science/pith/WXSM7OQYGVYC2SSYNWD4DIQQG2.json","view_paper":"https://pith.science/paper/WXSM7OQY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.05618&json=true","fetch_graph":"https://pith.science/api/pith-number/WXSM7OQYGVYC2SSYNWD4DIQQG2/graph.json","fetch_events":"https://pith.science/api/pith-number/WXSM7OQYGVYC2SSYNWD4DIQQG2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WXSM7OQYGVYC2SSYNWD4DIQQG2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WXSM7OQYGVYC2SSYNWD4DIQQG2/action/storage_attestation","attest_author":"https://pith.science/pith/WXSM7OQYGVYC2SSYNWD4DIQQG2/action/author_attestation","sign_citation":"https://pith.science/pith/WXSM7OQYGVYC2SSYNWD4DIQQG2/action/citation_signature","submit_replication":"https://pith.science/pith/WXSM7OQYGVYC2SSYNWD4DIQQG2/action/replication_record"}},"created_at":"2026-05-18T00:13:14.582934+00:00","updated_at":"2026-05-18T00:13:14.582934+00:00"}