{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:6NTN4ALPWD6C6GESN5AWB6KAWA","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":"07765a8b76e1e106b3e53ee1a33312d96f86aad3d302fd5ec0d6fac1a73d14ff","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-22T01:02:55Z","title_canon_sha256":"dbac0fa3494bd936620d3762067c77f1addb892e61df6a158e476ba87eae4020"},"schema_version":"1.0","source":{"id":"2010.11364","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.11364","created_at":"2026-07-05T02:01:55Z"},{"alias_kind":"arxiv_version","alias_value":"2010.11364v2","created_at":"2026-07-05T02:01:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.11364","created_at":"2026-07-05T02:01:55Z"},{"alias_kind":"pith_short_12","alias_value":"6NTN4ALPWD6C","created_at":"2026-07-05T02:01:55Z"},{"alias_kind":"pith_short_16","alias_value":"6NTN4ALPWD6C6GES","created_at":"2026-07-05T02:01:55Z"},{"alias_kind":"pith_short_8","alias_value":"6NTN4ALP","created_at":"2026-07-05T02:01:55Z"}],"graph_snapshots":[{"event_id":"sha256:1734ecc51c7068c5e8cc351b6fe9cc3a55264cd3fc8aef51adfb1f7fb406c478","target":"graph","created_at":"2026-07-05T02:01:55Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2010.11364/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Policy gradient methods are among the most effective methods for large-scale reinforcement learning, and their empirical success has prompted several works that develop the foundation of their global convergence theory. However, prior works have either required exact gradients or state-action visitation measure based mini-batch stochastic gradients with a diverging batch size, which limit their applicability in practical scenarios. In this paper, we consider classical policy gradient methods that compute an approximate gradient with a single trajectory or a fixed size mini-batch of trajectorie","authors_text":"Brendan O'Donoghue, Jongho Kim, Junzi Zhang, Stephen Boyd","cross_cats":["math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-22T01:02:55Z","title":"Sample Efficient Reinforcement Learning with REINFORCE"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.11364","kind":"arxiv","version":2},"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:aa328697d24fa3f6bb201891aeb52c89bb5872921ed71fee4de1b1c41d30f3d4","target":"record","created_at":"2026-07-05T02:01:55Z","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":"07765a8b76e1e106b3e53ee1a33312d96f86aad3d302fd5ec0d6fac1a73d14ff","cross_cats_sorted":["math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-22T01:02:55Z","title_canon_sha256":"dbac0fa3494bd936620d3762067c77f1addb892e61df6a158e476ba87eae4020"},"schema_version":"1.0","source":{"id":"2010.11364","kind":"arxiv","version":2}},"canonical_sha256":"f366de016fb0fc2f18926f4160f940b00bf05841084bb80e6a03642227720750","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f366de016fb0fc2f18926f4160f940b00bf05841084bb80e6a03642227720750","first_computed_at":"2026-07-05T02:01:55.181159Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:01:55.181159Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"m+GcImGnkp3dW2VF0LOkOq0HQaviOIYQmf4y65zfXxn7oX2Rqfmb5kLjhoHZAtdgLWgWrCd0i6FXJQe2tQ0TCw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:01:55.181601Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.11364","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aa328697d24fa3f6bb201891aeb52c89bb5872921ed71fee4de1b1c41d30f3d4","sha256:1734ecc51c7068c5e8cc351b6fe9cc3a55264cd3fc8aef51adfb1f7fb406c478"],"state_sha256":"64f9f8bbd37824cbe503e7f3b9350bdfff73d1e727f1116a8bc92cbfc282b75f"}