{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2013:UKOXY56QHBJEVEZY63XTLGS7OR","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":"51205d32ac70a94d8142adcd291dcc7e6f16f73e7e0c592c22384d976eb787c7","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-01-10T16:26:53Z","title_canon_sha256":"0512690abe75423e8d2b65f491496bad633cede55d51dda2379cb0e94f068227"},"schema_version":"1.0","source":{"id":"1301.2315","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1301.2315","created_at":"2026-05-18T03:36:45Z"},{"alias_kind":"arxiv_version","alias_value":"1301.2315v1","created_at":"2026-05-18T03:36:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1301.2315","created_at":"2026-05-18T03:36:45Z"},{"alias_kind":"pith_short_12","alias_value":"UKOXY56QHBJE","created_at":"2026-05-18T12:28:02Z"},{"alias_kind":"pith_short_16","alias_value":"UKOXY56QHBJEVEZY","created_at":"2026-05-18T12:28:02Z"},{"alias_kind":"pith_short_8","alias_value":"UKOXY56Q","created_at":"2026-05-18T12:28:02Z"}],"graph_snapshots":[{"event_id":"sha256:9f519cb97a40dd0f2de27c1e5188713e5eac194278be56f4ce41cdd0c16b34df","target":"graph","created_at":"2026-05-18T03:36:45Z","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":"There exist a number of reinforcement learning algorithms which learnby climbing the gradient of expected reward.  Their long-runconvergence has been proved, even in partially observableenvironments with non-deterministic actions, and without the need fora system model.  However, the variance of the gradient estimator hasbeen found to be a significant practical problem.  Recent approacheshave discounted future rewards, introducing a bias-variance trade-offinto the gradient estimate.  We incorporate a reward baseline into thelearning system, and show that it affects variance without introducing","authors_text":"Lex Weaver, Nigel Tao","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-01-10T16:26:53Z","title":"The Optimal Reward Baseline for Gradient-Based Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1301.2315","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:d7caea2201ee536972ec9db49ddf38b2f7c2c770732f90ce6c4fb02bbc097bd4","target":"record","created_at":"2026-05-18T03:36:45Z","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":"51205d32ac70a94d8142adcd291dcc7e6f16f73e7e0c592c22384d976eb787c7","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-01-10T16:26:53Z","title_canon_sha256":"0512690abe75423e8d2b65f491496bad633cede55d51dda2379cb0e94f068227"},"schema_version":"1.0","source":{"id":"1301.2315","kind":"arxiv","version":1}},"canonical_sha256":"a29d7c77d038524a9338f6ef359a5f746306b661bbc67240f3b9fdbbd46d9ff4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a29d7c77d038524a9338f6ef359a5f746306b661bbc67240f3b9fdbbd46d9ff4","first_computed_at":"2026-05-18T03:36:45.340956Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:36:45.340956Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"V8NwyKb+N9F+mAtgY6pkwprGNm4MAFj1oqA13uNdwvECXfTth0qZK/Pso0+4pbQOJFJysZMlNabIID40vXt2Bg==","signature_status":"signed_v1","signed_at":"2026-05-18T03:36:45.341659Z","signed_message":"canonical_sha256_bytes"},"source_id":"1301.2315","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d7caea2201ee536972ec9db49ddf38b2f7c2c770732f90ce6c4fb02bbc097bd4","sha256:9f519cb97a40dd0f2de27c1e5188713e5eac194278be56f4ce41cdd0c16b34df"],"state_sha256":"0fa5c95c95ae022a38e8456699e75a9f5cca58144997510cb295700621b53d9b"}