{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NUGHDQOTKGZX4A5ARCFCXU4EE7","short_pith_number":"pith:NUGHDQOT","schema_version":"1.0","canonical_sha256":"6d0c71c1d351b37e03a0888a2bd38427f3e70e7aedffa5eea1d5553526d4f188","source":{"kind":"arxiv","id":"2507.08793","version":2},"attestation_state":"computed","paper":{"title":"Optimistic Exploration for Risk-Averse Constrained Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Elizabeth Daly, Ivana Dusparic, James McCarthy, Radu Marinescu","submitted_at":"2025-07-11T17:54:54Z","abstract_excerpt":"Risk-averse Constrained Reinforcement Learning (RaCRL) aims to learn policies that minimise the likelihood of rare and catastrophic constraint violations caused by an environment's inherent randomness. In general, risk-aversion leads to conservative exploration of the environment which typically results in converging to sub-optimal policies that fail to adequately maximise reward or, in some cases, fail to achieve the goal. In this paper, we propose an exploration-based approach for RaCRL called Optimistic Risk-averse Actor Critic (ORAC), which constructs an exploratory policy by maximising a "},"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":"2507.08793","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-11T17:54:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"dc89cde79e4fb3a6e0bf515a841f6e09537dc0bf95cc93b2f0c8ca1d53a75652","abstract_canon_sha256":"536886091cdf77179494322c7185369317d3af04750fda599a7681418151967f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:00:04.073535Z","signature_b64":"TD0iHocbVxyI0EMKbUQ/LeiX5rARNczjCnw14HT83ebEvpNaOOApYwLF2uekHu3fbgR3+CK1nTtAGwachPfeAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d0c71c1d351b37e03a0888a2bd38427f3e70e7aedffa5eea1d5553526d4f188","last_reissued_at":"2026-07-05T12:00:04.073108Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:00:04.073108Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimistic Exploration for Risk-Averse Constrained Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Elizabeth Daly, Ivana Dusparic, James McCarthy, Radu Marinescu","submitted_at":"2025-07-11T17:54:54Z","abstract_excerpt":"Risk-averse Constrained Reinforcement Learning (RaCRL) aims to learn policies that minimise the likelihood of rare and catastrophic constraint violations caused by an environment's inherent randomness. In general, risk-aversion leads to conservative exploration of the environment which typically results in converging to sub-optimal policies that fail to adequately maximise reward or, in some cases, fail to achieve the goal. In this paper, we propose an exploration-based approach for RaCRL called Optimistic Risk-averse Actor Critic (ORAC), which constructs an exploratory policy by maximising a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.08793","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/2507.08793/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":"2507.08793","created_at":"2026-07-05T12:00:04.073165+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.08793v2","created_at":"2026-07-05T12:00:04.073165+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.08793","created_at":"2026-07-05T12:00:04.073165+00:00"},{"alias_kind":"pith_short_12","alias_value":"NUGHDQOTKGZX","created_at":"2026-07-05T12:00:04.073165+00:00"},{"alias_kind":"pith_short_16","alias_value":"NUGHDQOTKGZX4A5A","created_at":"2026-07-05T12:00:04.073165+00:00"},{"alias_kind":"pith_short_8","alias_value":"NUGHDQOT","created_at":"2026-07-05T12:00:04.073165+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NUGHDQOTKGZX4A5ARCFCXU4EE7","json":"https://pith.science/pith/NUGHDQOTKGZX4A5ARCFCXU4EE7.json","graph_json":"https://pith.science/api/pith-number/NUGHDQOTKGZX4A5ARCFCXU4EE7/graph.json","events_json":"https://pith.science/api/pith-number/NUGHDQOTKGZX4A5ARCFCXU4EE7/events.json","paper":"https://pith.science/paper/NUGHDQOT"},"agent_actions":{"view_html":"https://pith.science/pith/NUGHDQOTKGZX4A5ARCFCXU4EE7","download_json":"https://pith.science/pith/NUGHDQOTKGZX4A5ARCFCXU4EE7.json","view_paper":"https://pith.science/paper/NUGHDQOT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.08793&json=true","fetch_graph":"https://pith.science/api/pith-number/NUGHDQOTKGZX4A5ARCFCXU4EE7/graph.json","fetch_events":"https://pith.science/api/pith-number/NUGHDQOTKGZX4A5ARCFCXU4EE7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NUGHDQOTKGZX4A5ARCFCXU4EE7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NUGHDQOTKGZX4A5ARCFCXU4EE7/action/storage_attestation","attest_author":"https://pith.science/pith/NUGHDQOTKGZX4A5ARCFCXU4EE7/action/author_attestation","sign_citation":"https://pith.science/pith/NUGHDQOTKGZX4A5ARCFCXU4EE7/action/citation_signature","submit_replication":"https://pith.science/pith/NUGHDQOTKGZX4A5ARCFCXU4EE7/action/replication_record"}},"created_at":"2026-07-05T12:00:04.073165+00:00","updated_at":"2026-07-05T12:00:04.073165+00:00"}