{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OFRXNAW3BS6Y64QJLVP5SEG7MH","short_pith_number":"pith:OFRXNAW3","schema_version":"1.0","canonical_sha256":"71637682db0cbd8f72095d5fd910df61f78c4b7e173628db77eaefa22c883dba","source":{"kind":"arxiv","id":"2402.09992","version":1},"attestation_state":"computed","paper":{"title":"Risk-Sensitive Soft Actor-Critic for Robust Deep Reinforcement Learning under Distribution Shifts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"James Harrison, Maximilian Schiffer, Tobias Enders","submitted_at":"2024-02-15T14:55:38Z","abstract_excerpt":"We study the robustness of deep reinforcement learning algorithms against distribution shifts within contextual multi-stage stochastic combinatorial optimization problems from the operations research domain. In this context, risk-sensitive algorithms promise to learn robust policies. While this field is of general interest to the reinforcement learning community, most studies up-to-date focus on theoretical results rather than real-world performance. With this work, we aim to bridge this gap by formally deriving a novel risk-sensitive deep reinforcement learning algorithm while providing numer"},"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":"2402.09992","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-15T14:55:38Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"fb382541abcc6c1be807dc672f95ad3a0c48248aff69c7c752ec217d360e5a39","abstract_canon_sha256":"c9bbc6d957ab0a7d4284be6f7d1c585ce646147d4a72cd76242513456b88d9b1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:45:39.980437Z","signature_b64":"dzsigh/Qf3ggvMKSJKTyuYnHuZBZateHowFxNrjtCf8RUevihim90WdxIG98/hEEisxtZKUariUKR99WJEP5Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"71637682db0cbd8f72095d5fd910df61f78c4b7e173628db77eaefa22c883dba","last_reissued_at":"2026-07-05T07:45:39.979986Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:45:39.979986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Risk-Sensitive Soft Actor-Critic for Robust Deep Reinforcement Learning under Distribution Shifts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"James Harrison, Maximilian Schiffer, Tobias Enders","submitted_at":"2024-02-15T14:55:38Z","abstract_excerpt":"We study the robustness of deep reinforcement learning algorithms against distribution shifts within contextual multi-stage stochastic combinatorial optimization problems from the operations research domain. In this context, risk-sensitive algorithms promise to learn robust policies. While this field is of general interest to the reinforcement learning community, most studies up-to-date focus on theoretical results rather than real-world performance. With this work, we aim to bridge this gap by formally deriving a novel risk-sensitive deep reinforcement learning algorithm while providing numer"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.09992","kind":"arxiv","version":1},"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/2402.09992/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":"2402.09992","created_at":"2026-07-05T07:45:39.980046+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.09992v1","created_at":"2026-07-05T07:45:39.980046+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.09992","created_at":"2026-07-05T07:45:39.980046+00:00"},{"alias_kind":"pith_short_12","alias_value":"OFRXNAW3BS6Y","created_at":"2026-07-05T07:45:39.980046+00:00"},{"alias_kind":"pith_short_16","alias_value":"OFRXNAW3BS6Y64QJ","created_at":"2026-07-05T07:45:39.980046+00:00"},{"alias_kind":"pith_short_8","alias_value":"OFRXNAW3","created_at":"2026-07-05T07:45:39.980046+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"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":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08053","citing_title":"Reinforcement Learning for Exponential Utility: Algorithms and Convergence in Discounted MDPs","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OFRXNAW3BS6Y64QJLVP5SEG7MH","json":"https://pith.science/pith/OFRXNAW3BS6Y64QJLVP5SEG7MH.json","graph_json":"https://pith.science/api/pith-number/OFRXNAW3BS6Y64QJLVP5SEG7MH/graph.json","events_json":"https://pith.science/api/pith-number/OFRXNAW3BS6Y64QJLVP5SEG7MH/events.json","paper":"https://pith.science/paper/OFRXNAW3"},"agent_actions":{"view_html":"https://pith.science/pith/OFRXNAW3BS6Y64QJLVP5SEG7MH","download_json":"https://pith.science/pith/OFRXNAW3BS6Y64QJLVP5SEG7MH.json","view_paper":"https://pith.science/paper/OFRXNAW3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.09992&json=true","fetch_graph":"https://pith.science/api/pith-number/OFRXNAW3BS6Y64QJLVP5SEG7MH/graph.json","fetch_events":"https://pith.science/api/pith-number/OFRXNAW3BS6Y64QJLVP5SEG7MH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OFRXNAW3BS6Y64QJLVP5SEG7MH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OFRXNAW3BS6Y64QJLVP5SEG7MH/action/storage_attestation","attest_author":"https://pith.science/pith/OFRXNAW3BS6Y64QJLVP5SEG7MH/action/author_attestation","sign_citation":"https://pith.science/pith/OFRXNAW3BS6Y64QJLVP5SEG7MH/action/citation_signature","submit_replication":"https://pith.science/pith/OFRXNAW3BS6Y64QJLVP5SEG7MH/action/replication_record"}},"created_at":"2026-07-05T07:45:39.980046+00:00","updated_at":"2026-07-05T07:45:39.980046+00:00"}