{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:WIYNHGGTVRDCYML4PEJISMSIRD","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":"d7493c9046d31c2ef4137cf1b9f7d146dd70eb1bf94a2b9db9a47a3c6ecc6c9e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-09T06:24:43Z","title_canon_sha256":"7bd7d8ba9c1e23947f4f35f33590c1392702bf304f0644104fb600ba54fff026"},"schema_version":"1.0","source":{"id":"1911.03618","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.03618","created_at":"2026-07-05T00:18:14Z"},{"alias_kind":"arxiv_version","alias_value":"1911.03618v1","created_at":"2026-07-05T00:18:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.03618","created_at":"2026-07-05T00:18:14Z"},{"alias_kind":"pith_short_12","alias_value":"WIYNHGGTVRDC","created_at":"2026-07-05T00:18:14Z"},{"alias_kind":"pith_short_16","alias_value":"WIYNHGGTVRDCYML4","created_at":"2026-07-05T00:18:14Z"},{"alias_kind":"pith_short_8","alias_value":"WIYNHGGT","created_at":"2026-07-05T00:18:14Z"}],"graph_snapshots":[{"event_id":"sha256:3a1be7615107cc1c392888c8fd5f4b5699489ac25dd0af61be1b467d972eb196","target":"graph","created_at":"2026-07-05T00:18:14Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1911.03618/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in deep reinforcement learning have demonstrated the capability of learning complex control policies from many types of environments. When learning policies for safety-critical applications, it is essential to be sensitive to risks and avoid catastrophic events. Towards this goal, we propose an actor-critic framework that models the uncertainty of the future and simultaneously learns a policy based on that uncertainty model. Specifically, given a distribution of the future return for any state and action, we optimize policies for varying levels of conditional Value-at-Risk. The","authors_text":"Jian Zhang, Ruslan Salakhutdinov, Yichuan Charlie Tang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-09T06:24:43Z","title":"Worst Cases Policy Gradients"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.03618","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":"sha256:0f086c415feb05ff19b9ab5874618c0d566155863a323d92ea65f6e2867c91a1","target":"record","created_at":"2026-07-05T00:18:14Z","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":"d7493c9046d31c2ef4137cf1b9f7d146dd70eb1bf94a2b9db9a47a3c6ecc6c9e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-09T06:24:43Z","title_canon_sha256":"7bd7d8ba9c1e23947f4f35f33590c1392702bf304f0644104fb600ba54fff026"},"schema_version":"1.0","source":{"id":"1911.03618","kind":"arxiv","version":1}},"canonical_sha256":"b230d398d3ac462c317c791289324888cc19d3fea96c3ed2b3143f1e37825988","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b230d398d3ac462c317c791289324888cc19d3fea96c3ed2b3143f1e37825988","first_computed_at":"2026-07-05T00:18:14.307350Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:18:14.307350Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xal0JA4quMBmWyNMIIoKG8r9/HJm18nyzBpb1FVNFdFt26bbKjKXzs6sCKoyESb1o9YjPgjaWh4ll1oxwOQHCg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:18:14.307731Z","signed_message":"canonical_sha256_bytes"},"source_id":"1911.03618","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0f086c415feb05ff19b9ab5874618c0d566155863a323d92ea65f6e2867c91a1","sha256:3a1be7615107cc1c392888c8fd5f4b5699489ac25dd0af61be1b467d972eb196"],"state_sha256":"c92d24d5d6256573d017515ec0f7abc7c4698765cd76fee13d2c6b3948021d15"}