{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VIYWHVMG6XT3HFE5N67SVK7SXB","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":"69ce2f667c136b3ff994984b7a48537abefb4227218d12d3f9bba74f516536e6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-23T09:48:48Z","title_canon_sha256":"a9528f6ca8baa46d30b2a69ed776d4cf9266f53dff56f298e862560ba80d4a14"},"schema_version":"1.0","source":{"id":"2405.14372","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.14372","created_at":"2026-07-05T09:12:06Z"},{"alias_kind":"arxiv_version","alias_value":"2405.14372v2","created_at":"2026-07-05T09:12:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.14372","created_at":"2026-07-05T09:12:06Z"},{"alias_kind":"pith_short_12","alias_value":"VIYWHVMG6XT3","created_at":"2026-07-05T09:12:06Z"},{"alias_kind":"pith_short_16","alias_value":"VIYWHVMG6XT3HFE5","created_at":"2026-07-05T09:12:06Z"},{"alias_kind":"pith_short_8","alias_value":"VIYWHVMG","created_at":"2026-07-05T09:12:06Z"}],"graph_snapshots":[{"event_id":"sha256:033f8fc96cae3249d466e6e3c41176aec9361c3f1ab2538d45add24d7eaf3a50","target":"graph","created_at":"2026-07-05T09:12:06Z","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/2405.14372/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In constrained Markov decision processes (CMDPs) with adversarial rewards and constraints, a well-known impossibility result prevents any algorithm from attaining both sublinear regret and sublinear constraint violation, when competing against a best-in-hindsight policy that satisfies constraints on average. In this paper, we show that this negative result can be eased in CMDPs with non-stationary rewards and constraints, by providing algorithms whose performances smoothly degrade as non-stationarity increases. Specifically, we propose algorithms attaining $\\tilde{\\mathcal{O}} (\\sqrt{T} + C)$ ","authors_text":"Alberto Marchesi, Anna Lunghi, Francesco Emanuele Stradi, Matteo Castiglioni, Nicola Gatti","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-23T09:48:48Z","title":"Learning Constrained Markov Decision Processes With Non-stationary Rewards and Constraints"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.14372","kind":"arxiv","version":2},"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":"sha256:6e6aa51f8caf78d6a74008a147ed68f3169e20283b32513c2f28ed02cf5b367e","target":"record","created_at":"2026-07-05T09:12:06Z","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":"69ce2f667c136b3ff994984b7a48537abefb4227218d12d3f9bba74f516536e6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-23T09:48:48Z","title_canon_sha256":"a9528f6ca8baa46d30b2a69ed776d4cf9266f53dff56f298e862560ba80d4a14"},"schema_version":"1.0","source":{"id":"2405.14372","kind":"arxiv","version":2}},"canonical_sha256":"aa3163d586f5e7b3949d6fbf2aabf2b85ce11c6df61bfb1856fdc7cf7a39cd45","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aa3163d586f5e7b3949d6fbf2aabf2b85ce11c6df61bfb1856fdc7cf7a39cd45","first_computed_at":"2026-07-05T09:12:06.409928Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:12:06.409928Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"X448YkU74+2ml/twQG50EtU7lvGvx1IbDOp5F2/snbJzzc5k5gp5zskTHqUUKRrnnDfokbmbm5sVdIDW8HqEAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:12:06.410440Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.14372","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6e6aa51f8caf78d6a74008a147ed68f3169e20283b32513c2f28ed02cf5b367e","sha256:033f8fc96cae3249d466e6e3c41176aec9361c3f1ab2538d45add24d7eaf3a50"],"state_sha256":"f65bf0b0b1cfbc853bbdb948f2be06639a77c34815f4c7476b6d45dcc89655fa"}