{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:J43NESKQVRCP3V35QUNJMQPAF3","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":"001ab86fd921e0d435d492d24bc643fe2fb03a8f3e1b7304b91e5c59380b5424","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-14T18:29:02Z","title_canon_sha256":"01778ea2ee3c965b40e49831b4140b924047a121edb6831c61a9f06179039774"},"schema_version":"1.0","source":{"id":"2209.06866","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.06866","created_at":"2026-07-05T04:57:49Z"},{"alias_kind":"arxiv_version","alias_value":"2209.06866v1","created_at":"2026-07-05T04:57:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.06866","created_at":"2026-07-05T04:57:49Z"},{"alias_kind":"pith_short_12","alias_value":"J43NESKQVRCP","created_at":"2026-07-05T04:57:49Z"},{"alias_kind":"pith_short_16","alias_value":"J43NESKQVRCP3V35","created_at":"2026-07-05T04:57:49Z"},{"alias_kind":"pith_short_8","alias_value":"J43NESKQ","created_at":"2026-07-05T04:57:49Z"}],"graph_snapshots":[{"event_id":"sha256:751e59f2678f81d7c214530a369be23b5b7184aaed39a079371b832efe61f83d","target":"graph","created_at":"2026-07-05T04:57:49Z","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/2209.06866/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Fei Miao, Shaofeng Zou, Yue Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-14T18:29:02Z","title":"Robust Constrained Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.06866","kind":"arxiv","version":1},"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:e29c851297427f54f9db211fe0ea6d218eea52b93e70655c8dcab7f777174bea","target":"record","created_at":"2026-07-05T04:57:49Z","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":"001ab86fd921e0d435d492d24bc643fe2fb03a8f3e1b7304b91e5c59380b5424","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-14T18:29:02Z","title_canon_sha256":"01778ea2ee3c965b40e49831b4140b924047a121edb6831c61a9f06179039774"},"schema_version":"1.0","source":{"id":"2209.06866","kind":"arxiv","version":1}},"canonical_sha256":"4f36d24950ac44fdd77d851a9641e02ed5ba46979d88c9580f8b79ea0564536d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4f36d24950ac44fdd77d851a9641e02ed5ba46979d88c9580f8b79ea0564536d","first_computed_at":"2026-07-05T04:57:49.374461Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:57:49.374461Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"epEUw32eNpWKc/vqmXMRIg0BG9hXnM7EEdXBtO134n7cw3SPz2NPqZvgVnBm3+KQRp8YZRS0A5DkTGWxOMDDDA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:57:49.375004Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.06866","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e29c851297427f54f9db211fe0ea6d218eea52b93e70655c8dcab7f777174bea","sha256:751e59f2678f81d7c214530a369be23b5b7184aaed39a079371b832efe61f83d"],"state_sha256":"5c321e4231ef0e0543f3246937b5bb4b4b705fa811a53a03735521d15702137e"}