{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:ROTBDD6WBKF3JS2O3J74MDX5KB","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":"9ef78ba82c758872ec6f26d400291184a58646a02e2e874aa3f79f6f28c2bc0f","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-30T01:36:16Z","title_canon_sha256":"5d61cb88811ce9e0a6754762aa69d6d6e21570ad55fc827c0125840d0fd3a9ec"},"schema_version":"1.0","source":{"id":"2011.14495","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.14495","created_at":"2026-07-05T02:18:45Z"},{"alias_kind":"arxiv_version","alias_value":"2011.14495v2","created_at":"2026-07-05T02:18:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.14495","created_at":"2026-07-05T02:18:45Z"},{"alias_kind":"pith_short_12","alias_value":"ROTBDD6WBKF3","created_at":"2026-07-05T02:18:45Z"},{"alias_kind":"pith_short_16","alias_value":"ROTBDD6WBKF3JS2O","created_at":"2026-07-05T02:18:45Z"},{"alias_kind":"pith_short_8","alias_value":"ROTBDD6W","created_at":"2026-07-05T02:18:45Z"}],"graph_snapshots":[{"event_id":"sha256:be5ceb4e4e89b4858e096e5228497f27decfa07489e78a790692ed56f3d910de","target":"graph","created_at":"2026-07-05T02:18:45Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2011.14495/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In reinforcement learning, robust policies for high-stakes decision-making problems with limited data are usually computed by optimizing the percentile criterion, which minimizes the probability of a catastrophic failure. Unfortunately, such policies are typically overly conservative as the percentile criterion is non-convex, difficult to optimize, and ignores the mean performance. To overcome these shortcomings, we study the soft-robust criterion, which uses risk measures to balance the mean and percentile criterion better. In this paper, we establish the soft-robust criterion's fundamental p","authors_text":"Elita A. Lobo, Marek Petrik, Mohammad Ghavamzadeh","cross_cats":["cs.AI","math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-30T01:36:16Z","title":"Soft-Robust Algorithms for Batch Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.14495","kind":"arxiv","version":2},"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":"sha256:83f8ed4fe9204faa07b7482f7b0577c9331b755fff2826b39f5107942253d311","target":"record","created_at":"2026-07-05T02:18:45Z","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":"9ef78ba82c758872ec6f26d400291184a58646a02e2e874aa3f79f6f28c2bc0f","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-30T01:36:16Z","title_canon_sha256":"5d61cb88811ce9e0a6754762aa69d6d6e21570ad55fc827c0125840d0fd3a9ec"},"schema_version":"1.0","source":{"id":"2011.14495","kind":"arxiv","version":2}},"canonical_sha256":"8ba6118fd60a8bb4cb4eda7fc60efd505a13e3d7ce007336a83219184f690a03","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8ba6118fd60a8bb4cb4eda7fc60efd505a13e3d7ce007336a83219184f690a03","first_computed_at":"2026-07-05T02:18:45.482869Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:18:45.482869Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7emPosXq8jJE0eVKlQpRxjHo58TEMfyNLnc0H2fl5XHRJ/+YvzDUErJwe7i2fomAI21kLoVFo/wBU6TlFpx+Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:18:45.483307Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.14495","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:83f8ed4fe9204faa07b7482f7b0577c9331b755fff2826b39f5107942253d311","sha256:be5ceb4e4e89b4858e096e5228497f27decfa07489e78a790692ed56f3d910de"],"state_sha256":"88dceeb665db2178fc2a27660610fbe0e1cbcf4f7fd3579dfbc4273cfa7da82d"}