{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HWTVUEXSCENSYO4ZGBYLV2I44E","short_pith_number":"pith:HWTVUEXS","schema_version":"1.0","canonical_sha256":"3da75a12f2111b2c3b993070bae91ce134fbabbae071ccc92bbdba2b22e854a6","source":{"kind":"arxiv","id":"2411.03107","version":1},"attestation_state":"computed","paper":{"title":"Near-Optimal Dynamic Regret for Adversarial Linear Mixture MDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Long-Fei Li, Peng Zhao, Zhi-Hua Zhou","submitted_at":"2024-11-05T13:55:52Z","abstract_excerpt":"We study episodic linear mixture MDPs with the unknown transition and adversarial rewards under full-information feedback, employing dynamic regret as the performance measure. We start with in-depth analyses of the strengths and limitations of the two most popular methods: occupancy-measure-based and policy-based methods. We observe that while the occupancy-measure-based method is effective in addressing non-stationary environments, it encounters difficulties with the unknown transition. In contrast, the policy-based method can deal with the unknown transition effectively but faces challenges "},"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":"2411.03107","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-05T13:55:52Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"622c75b972a318462bacb77b7e4cc6d9ba953fe2d11730f6be4101f9c800ce27","abstract_canon_sha256":"18097b700a717d064f4012c35de950e992396dbf619c8272d87ba7f800f9f29b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:31:25.514938Z","signature_b64":"fn7bH3xu+T/9+HHTJfI9H/5hRKpApOPEFTAboNmRsDohdlA7Pam0y5XqNJxHm/DedorVs4MVC9a3jyj3b6UnAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3da75a12f2111b2c3b993070bae91ce134fbabbae071ccc92bbdba2b22e854a6","last_reissued_at":"2026-07-05T09:31:25.514449Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:31:25.514449Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Near-Optimal Dynamic Regret for Adversarial Linear Mixture MDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Long-Fei Li, Peng Zhao, Zhi-Hua Zhou","submitted_at":"2024-11-05T13:55:52Z","abstract_excerpt":"We study episodic linear mixture MDPs with the unknown transition and adversarial rewards under full-information feedback, employing dynamic regret as the performance measure. We start with in-depth analyses of the strengths and limitations of the two most popular methods: occupancy-measure-based and policy-based methods. We observe that while the occupancy-measure-based method is effective in addressing non-stationary environments, it encounters difficulties with the unknown transition. In contrast, the policy-based method can deal with the unknown transition effectively but faces challenges "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.03107","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/2411.03107/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":"2411.03107","created_at":"2026-07-05T09:31:25.514509+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.03107v1","created_at":"2026-07-05T09:31:25.514509+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.03107","created_at":"2026-07-05T09:31:25.514509+00:00"},{"alias_kind":"pith_short_12","alias_value":"HWTVUEXSCENS","created_at":"2026-07-05T09:31:25.514509+00:00"},{"alias_kind":"pith_short_16","alias_value":"HWTVUEXSCENSYO4Z","created_at":"2026-07-05T09:31:25.514509+00:00"},{"alias_kind":"pith_short_8","alias_value":"HWTVUEXS","created_at":"2026-07-05T09:31:25.514509+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.29092","citing_title":"Priced Motion Through Optimal Faces: A Normal-Fan Geometry for Non-Stationary Adversarial MDPs","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HWTVUEXSCENSYO4ZGBYLV2I44E","json":"https://pith.science/pith/HWTVUEXSCENSYO4ZGBYLV2I44E.json","graph_json":"https://pith.science/api/pith-number/HWTVUEXSCENSYO4ZGBYLV2I44E/graph.json","events_json":"https://pith.science/api/pith-number/HWTVUEXSCENSYO4ZGBYLV2I44E/events.json","paper":"https://pith.science/paper/HWTVUEXS"},"agent_actions":{"view_html":"https://pith.science/pith/HWTVUEXSCENSYO4ZGBYLV2I44E","download_json":"https://pith.science/pith/HWTVUEXSCENSYO4ZGBYLV2I44E.json","view_paper":"https://pith.science/paper/HWTVUEXS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.03107&json=true","fetch_graph":"https://pith.science/api/pith-number/HWTVUEXSCENSYO4ZGBYLV2I44E/graph.json","fetch_events":"https://pith.science/api/pith-number/HWTVUEXSCENSYO4ZGBYLV2I44E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HWTVUEXSCENSYO4ZGBYLV2I44E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HWTVUEXSCENSYO4ZGBYLV2I44E/action/storage_attestation","attest_author":"https://pith.science/pith/HWTVUEXSCENSYO4ZGBYLV2I44E/action/author_attestation","sign_citation":"https://pith.science/pith/HWTVUEXSCENSYO4ZGBYLV2I44E/action/citation_signature","submit_replication":"https://pith.science/pith/HWTVUEXSCENSYO4ZGBYLV2I44E/action/replication_record"}},"created_at":"2026-07-05T09:31:25.514509+00:00","updated_at":"2026-07-05T09:31:25.514509+00:00"}