{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:J43NESKQVRCP3V35QUNJMQPAF3","short_pith_number":"pith:J43NESKQ","schema_version":"1.0","canonical_sha256":"4f36d24950ac44fdd77d851a9641e02ed5ba46979d88c9580f8b79ea0564536d","source":{"kind":"arxiv","id":"2209.06866","version":1},"attestation_state":"computed","paper":{"title":"Robust Constrained Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Fei Miao, Shaofeng Zou, Yue Wang","submitted_at":"2022-09-14T18:29:02Z","abstract_excerpt":"Constrained reinforcement learning is to maximize the expected reward subject to constraints on utilities/costs. However, the training environment may not be the same as the test one, due to, e.g., modeling error, adversarial attack, non-stationarity, resulting in severe performance degradation and more importantly constraint violation. We propose a framework of robust constrained reinforcement learning under model uncertainty, where the MDP is not fixed but lies in some uncertainty set, the goal is to guarantee that constraints on utilities/costs are satisfied for all MDPs in the uncertainty "},"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":"2209.06866","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-14T18:29:02Z","cross_cats_sorted":[],"title_canon_sha256":"01778ea2ee3c965b40e49831b4140b924047a121edb6831c61a9f06179039774","abstract_canon_sha256":"001ab86fd921e0d435d492d24bc643fe2fb03a8f3e1b7304b91e5c59380b5424"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:57:49.375004Z","signature_b64":"epEUw32eNpWKc/vqmXMRIg0BG9hXnM7EEdXBtO134n7cw3SPz2NPqZvgVnBm3+KQRp8YZRS0A5DkTGWxOMDDDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f36d24950ac44fdd77d851a9641e02ed5ba46979d88c9580f8b79ea0564536d","last_reissued_at":"2026-07-05T04:57:49.374461Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:57:49.374461Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust Constrained Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Fei Miao, Shaofeng Zou, Yue Wang","submitted_at":"2022-09-14T18:29:02Z","abstract_excerpt":"Constrained reinforcement learning is to maximize the expected reward subject to constraints on utilities/costs. However, the training environment may not be the same as the test one, due to, e.g., modeling error, adversarial attack, non-stationarity, resulting in severe performance degradation and more importantly constraint violation. We propose a framework of robust constrained reinforcement learning under model uncertainty, where the MDP is not fixed but lies in some uncertainty set, the goal is to guarantee that constraints on utilities/costs are satisfied for all MDPs in the uncertainty "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.06866","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/2209.06866/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":"2209.06866","created_at":"2026-07-05T04:57:49.374514+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.06866v1","created_at":"2026-07-05T04:57:49.374514+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.06866","created_at":"2026-07-05T04:57:49.374514+00:00"},{"alias_kind":"pith_short_12","alias_value":"J43NESKQVRCP","created_at":"2026-07-05T04:57:49.374514+00:00"},{"alias_kind":"pith_short_16","alias_value":"J43NESKQVRCP3V35","created_at":"2026-07-05T04:57:49.374514+00:00"},{"alias_kind":"pith_short_8","alias_value":"J43NESKQ","created_at":"2026-07-05T04:57:49.374514+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2408.16286","citing_title":"Near-Optimal Policy Identification in Robust Constrained Markov Decision Processes via Epigraph Form","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14243","citing_title":"Optimistic Policy Learning under Pessimistic Adversaries with Regret and Violation Guarantees","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J43NESKQVRCP3V35QUNJMQPAF3","json":"https://pith.science/pith/J43NESKQVRCP3V35QUNJMQPAF3.json","graph_json":"https://pith.science/api/pith-number/J43NESKQVRCP3V35QUNJMQPAF3/graph.json","events_json":"https://pith.science/api/pith-number/J43NESKQVRCP3V35QUNJMQPAF3/events.json","paper":"https://pith.science/paper/J43NESKQ"},"agent_actions":{"view_html":"https://pith.science/pith/J43NESKQVRCP3V35QUNJMQPAF3","download_json":"https://pith.science/pith/J43NESKQVRCP3V35QUNJMQPAF3.json","view_paper":"https://pith.science/paper/J43NESKQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.06866&json=true","fetch_graph":"https://pith.science/api/pith-number/J43NESKQVRCP3V35QUNJMQPAF3/graph.json","fetch_events":"https://pith.science/api/pith-number/J43NESKQVRCP3V35QUNJMQPAF3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J43NESKQVRCP3V35QUNJMQPAF3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J43NESKQVRCP3V35QUNJMQPAF3/action/storage_attestation","attest_author":"https://pith.science/pith/J43NESKQVRCP3V35QUNJMQPAF3/action/author_attestation","sign_citation":"https://pith.science/pith/J43NESKQVRCP3V35QUNJMQPAF3/action/citation_signature","submit_replication":"https://pith.science/pith/J43NESKQVRCP3V35QUNJMQPAF3/action/replication_record"}},"created_at":"2026-07-05T04:57:49.374514+00:00","updated_at":"2026-07-05T04:57:49.374514+00:00"}