{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:ROTBDD6WBKF3JS2O3J74MDX5KB","short_pith_number":"pith:ROTBDD6W","schema_version":"1.0","canonical_sha256":"8ba6118fd60a8bb4cb4eda7fc60efd505a13e3d7ce007336a83219184f690a03","source":{"kind":"arxiv","id":"2011.14495","version":2},"attestation_state":"computed","paper":{"title":"Soft-Robust Algorithms for Batch Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Elita A. Lobo, Marek Petrik, Mohammad Ghavamzadeh","submitted_at":"2020-11-30T01:36:16Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2011.14495","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-30T01:36:16Z","cross_cats_sorted":["cs.AI","math.OC","stat.ML"],"title_canon_sha256":"5d61cb88811ce9e0a6754762aa69d6d6e21570ad55fc827c0125840d0fd3a9ec","abstract_canon_sha256":"9ef78ba82c758872ec6f26d400291184a58646a02e2e874aa3f79f6f28c2bc0f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:18:45.483307Z","signature_b64":"7emPosXq8jJE0eVKlQpRxjHo58TEMfyNLnc0H2fl5XHRJ/+YvzDUErJwe7i2fomAI21kLoVFo/wBU6TlFpx+Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ba6118fd60a8bb4cb4eda7fc60efd505a13e3d7ce007336a83219184f690a03","last_reissued_at":"2026-07-05T02:18:45.482869Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:18:45.482869Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Soft-Robust Algorithms for Batch Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Elita A. Lobo, Marek Petrik, Mohammad Ghavamzadeh","submitted_at":"2020-11-30T01:36:16Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.14495","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2011.14495/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2011.14495","created_at":"2026-07-05T02:18:45.482917+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.14495v2","created_at":"2026-07-05T02:18:45.482917+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.14495","created_at":"2026-07-05T02:18:45.482917+00:00"},{"alias_kind":"pith_short_12","alias_value":"ROTBDD6WBKF3","created_at":"2026-07-05T02:18:45.482917+00:00"},{"alias_kind":"pith_short_16","alias_value":"ROTBDD6WBKF3JS2O","created_at":"2026-07-05T02:18:45.482917+00:00"},{"alias_kind":"pith_short_8","alias_value":"ROTBDD6W","created_at":"2026-07-05T02:18:45.482917+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.12622","citing_title":"DR-SAC: Distributionally Robust Soft Actor-Critic for Reinforcement Learning under Uncertainty","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ROTBDD6WBKF3JS2O3J74MDX5KB","json":"https://pith.science/pith/ROTBDD6WBKF3JS2O3J74MDX5KB.json","graph_json":"https://pith.science/api/pith-number/ROTBDD6WBKF3JS2O3J74MDX5KB/graph.json","events_json":"https://pith.science/api/pith-number/ROTBDD6WBKF3JS2O3J74MDX5KB/events.json","paper":"https://pith.science/paper/ROTBDD6W"},"agent_actions":{"view_html":"https://pith.science/pith/ROTBDD6WBKF3JS2O3J74MDX5KB","download_json":"https://pith.science/pith/ROTBDD6WBKF3JS2O3J74MDX5KB.json","view_paper":"https://pith.science/paper/ROTBDD6W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.14495&json=true","fetch_graph":"https://pith.science/api/pith-number/ROTBDD6WBKF3JS2O3J74MDX5KB/graph.json","fetch_events":"https://pith.science/api/pith-number/ROTBDD6WBKF3JS2O3J74MDX5KB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ROTBDD6WBKF3JS2O3J74MDX5KB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ROTBDD6WBKF3JS2O3J74MDX5KB/action/storage_attestation","attest_author":"https://pith.science/pith/ROTBDD6WBKF3JS2O3J74MDX5KB/action/author_attestation","sign_citation":"https://pith.science/pith/ROTBDD6WBKF3JS2O3J74MDX5KB/action/citation_signature","submit_replication":"https://pith.science/pith/ROTBDD6WBKF3JS2O3J74MDX5KB/action/replication_record"}},"created_at":"2026-07-05T02:18:45.482917+00:00","updated_at":"2026-07-05T02:18:45.482917+00:00"}