{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:SQYHIOJF73S3FJVEZ42TDA545V","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":"1a75d76773d13c51e30752d14dff21b1d92b07e4c530a4e9e6b9180ec77c71c5","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-22T13:50:31Z","title_canon_sha256":"9bc9cf9e252ff714a7f246ae2e315910ea944bd16f21119023ec36f775fc1e36"},"schema_version":"1.0","source":{"id":"1908.08379","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.08379","created_at":"2026-07-04T23:59:12Z"},{"alias_kind":"arxiv_version","alias_value":"1908.08379v1","created_at":"2026-07-04T23:59:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.08379","created_at":"2026-07-04T23:59:12Z"},{"alias_kind":"pith_short_12","alias_value":"SQYHIOJF73S3","created_at":"2026-07-04T23:59:12Z"},{"alias_kind":"pith_short_16","alias_value":"SQYHIOJF73S3FJVE","created_at":"2026-07-04T23:59:12Z"},{"alias_kind":"pith_short_8","alias_value":"SQYHIOJF","created_at":"2026-07-04T23:59:12Z"}],"graph_snapshots":[{"event_id":"sha256:bac434fb4ca4b256ef76d356ac4a1b1eb1c3a577a812511dc4a1886982e6ea91","target":"graph","created_at":"2026-07-04T23:59:12Z","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/1908.08379/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Practical application of Reinforcement Learning (RL) often involves risk considerations. We study a generalized approximation scheme for risk measures, based on Monte-Carlo simulations, where the risk measures need not necessarily be \\emph{coherent}. We demonstrate that, even in simple problems, measures such as the variance of the reward-to-go do not capture the risk in a satisfactory manner. In addition, we show how a risk measure can be derived from model's realizations. We propose a neural architecture for estimating the risk and suggest the risk critic architecture that can be use to opti","authors_text":"Dotan Di Castro, Joel Oren, Shie Mannor","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-22T13:50:31Z","title":"Practical Risk Measures in Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.08379","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":"sha256:0e6b22c9520dee2d1c2322cc3e92bcc6a08186c84af95aaafc7bfdd44046467e","target":"record","created_at":"2026-07-04T23:59:12Z","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":"1a75d76773d13c51e30752d14dff21b1d92b07e4c530a4e9e6b9180ec77c71c5","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-22T13:50:31Z","title_canon_sha256":"9bc9cf9e252ff714a7f246ae2e315910ea944bd16f21119023ec36f775fc1e36"},"schema_version":"1.0","source":{"id":"1908.08379","kind":"arxiv","version":1}},"canonical_sha256":"9430743925fee5b2a6a4cf353183bced70200230fd32104ffb3eefd9660e7af2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9430743925fee5b2a6a4cf353183bced70200230fd32104ffb3eefd9660e7af2","first_computed_at":"2026-07-04T23:59:12.277344Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T23:59:12.277344Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aodCG7vI5T+7faMIEVYt8ZZiHHUEVzYxGxYVNg6uTQrDeRNDsAdDPZBq7FHGTq7yiBmq6Vi57R1rh8gOxTLTCg==","signature_status":"signed_v1","signed_at":"2026-07-04T23:59:12.277696Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.08379","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0e6b22c9520dee2d1c2322cc3e92bcc6a08186c84af95aaafc7bfdd44046467e","sha256:bac434fb4ca4b256ef76d356ac4a1b1eb1c3a577a812511dc4a1886982e6ea91"],"state_sha256":"734ee2dad80c39f943a37effa0e460259c995ce2499b5b89df2d55748e530e70"}