{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:UQK3EFNJRY4MGSPNBNJC3BFC2I","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":"b10265b7f08f4bc7f77303ad2f58ab694055d07db28a30656e24f0674a857bec","cross_cats_sorted":["cs.CY","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-06-27T19:59:59Z","title_canon_sha256":"c4d20cb6ca11df64033dbfceeb43ea25c83e2ed510e811c614f6d574399f6171"},"schema_version":"1.0","source":{"id":"1206.6404","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1206.6404","created_at":"2026-05-18T03:52:14Z"},{"alias_kind":"arxiv_version","alias_value":"1206.6404v1","created_at":"2026-05-18T03:52:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1206.6404","created_at":"2026-05-18T03:52:14Z"},{"alias_kind":"pith_short_12","alias_value":"UQK3EFNJRY4M","created_at":"2026-05-18T12:27:23Z"},{"alias_kind":"pith_short_16","alias_value":"UQK3EFNJRY4MGSPN","created_at":"2026-05-18T12:27:23Z"},{"alias_kind":"pith_short_8","alias_value":"UQK3EFNJ","created_at":"2026-05-18T12:27:23Z"}],"graph_snapshots":[{"event_id":"sha256:264f9d44269b012497c4e9c5008d03cd46461d7feedaa3b14386f4ace9e14a1a","target":"graph","created_at":"2026-05-18T03:52:14Z","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":"Managing risk in dynamic decision problems is of cardinal importance in many fields such as finance and process control. The most common approach to defining risk is through various variance related criteria such as the Sharpe Ratio or the standard deviation adjusted reward. It is known that optimizing many of the variance related risk criteria is NP-hard. In this paper we devise a framework for local policy gradient style algorithms for reinforcement learning for variance related criteria. Our starting point is a new formula for the variance of the cost-to-go in episodic tasks. Using this for","authors_text":"Aviv Tamar (Technion), Dotan Di Castro (Technion), Shie Mannor (Technion)","cross_cats":["cs.CY","math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-06-27T19:59:59Z","title":"Policy Gradients with Variance Related Risk Criteria"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1206.6404","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":"sha256:52961ece1efa424043d00f28ff5241c390576d96709330f97fa7592d25802e32","target":"record","created_at":"2026-05-18T03:52:14Z","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":"b10265b7f08f4bc7f77303ad2f58ab694055d07db28a30656e24f0674a857bec","cross_cats_sorted":["cs.CY","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2012-06-27T19:59:59Z","title_canon_sha256":"c4d20cb6ca11df64033dbfceeb43ea25c83e2ed510e811c614f6d574399f6171"},"schema_version":"1.0","source":{"id":"1206.6404","kind":"arxiv","version":1}},"canonical_sha256":"a415b215a98e38c349ed0b522d84a2d21d9348086db8c5eea8b1eb1f85d228a7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a415b215a98e38c349ed0b522d84a2d21d9348086db8c5eea8b1eb1f85d228a7","first_computed_at":"2026-05-18T03:52:14.407243Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:52:14.407243Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+htaI2r2Sa69/HMlpl2mfdVt8fHvSkEbJbNvx2L6JWXfK/JX87K8hScb6dFc7OzPqNxRUbYNMnprHOEWI4eNAg==","signature_status":"signed_v1","signed_at":"2026-05-18T03:52:14.407830Z","signed_message":"canonical_sha256_bytes"},"source_id":"1206.6404","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:52961ece1efa424043d00f28ff5241c390576d96709330f97fa7592d25802e32","sha256:264f9d44269b012497c4e9c5008d03cd46461d7feedaa3b14386f4ace9e14a1a"],"state_sha256":"6ed9d99e8cbd2b84f4d6dcb92728c68cd0aef1ac4841ac888e96799daa8fabdd"}