{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:ARSV4NVLK5UZNJOB6NS7Q4FOJU","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":"7a58d48183046dbb3ced11a56e7aa07d1d6aa6599d76a5eecc418ab89895ef30","cross_cats_sorted":["cs.LG","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-12-28T19:53:08Z","title_canon_sha256":"b9467bdafce9342ccae50b86d40babe1762435011450adb3856d250f6a8e9ce8"},"schema_version":"1.0","source":{"id":"1612.08967","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.08967","created_at":"2026-05-18T00:53:46Z"},{"alias_kind":"arxiv_version","alias_value":"1612.08967v1","created_at":"2026-05-18T00:53:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.08967","created_at":"2026-05-18T00:53:46Z"},{"alias_kind":"pith_short_12","alias_value":"ARSV4NVLK5UZ","created_at":"2026-05-18T12:30:07Z"},{"alias_kind":"pith_short_16","alias_value":"ARSV4NVLK5UZNJOB","created_at":"2026-05-18T12:30:07Z"},{"alias_kind":"pith_short_8","alias_value":"ARSV4NVL","created_at":"2026-05-18T12:30:07Z"}],"graph_snapshots":[{"event_id":"sha256:62628cfebc85117975c8ab85eb13a48a4e9351adb0396ff51fffc58ec3115037","target":"graph","created_at":"2026-05-18T00:53:46Z","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":"We tackle the issue of finding a good policy when the number of policy updates is limited. This is done by approximating the expected policy reward as a sequence of concave lower bounds which can be efficiently maximized, drastically reducing the number of policy updates required to achieve good performance. We also extend existing methods to negative rewards, enabling the use of control variates.","authors_text":"Nicolas Le Roux","cross_cats":["cs.LG","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-12-28T19:53:08Z","title":"Efficient iterative policy optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.08967","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:e7b6ebd21e1190bf4cbd32f16b772923a17f027ff1e661a38bac0942130aa272","target":"record","created_at":"2026-05-18T00:53:46Z","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":"7a58d48183046dbb3ced11a56e7aa07d1d6aa6599d76a5eecc418ab89895ef30","cross_cats_sorted":["cs.LG","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-12-28T19:53:08Z","title_canon_sha256":"b9467bdafce9342ccae50b86d40babe1762435011450adb3856d250f6a8e9ce8"},"schema_version":"1.0","source":{"id":"1612.08967","kind":"arxiv","version":1}},"canonical_sha256":"04655e36ab576996a5c1f365f870ae4d33aa364d964f93c041a5bdf0b028849e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"04655e36ab576996a5c1f365f870ae4d33aa364d964f93c041a5bdf0b028849e","first_computed_at":"2026-05-18T00:53:46.757454Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:53:46.757454Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"l9n4SRYylktyzWm/Y39lTFNwtPB8QLNHXzGr6yBVXtQI2k4rp3kXlGRiOGxEEv2lW7o/WAYWkJxf7HDewY/iDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:53:46.757816Z","signed_message":"canonical_sha256_bytes"},"source_id":"1612.08967","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e7b6ebd21e1190bf4cbd32f16b772923a17f027ff1e661a38bac0942130aa272","sha256:62628cfebc85117975c8ab85eb13a48a4e9351adb0396ff51fffc58ec3115037"],"state_sha256":"5aa065a698fb9675b30a8ffc09d94a06bbd79c672588f4e5029d32c11449fece"}