{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:N6CLX3TTAV7G2E7VUZPUIT73BG","short_pith_number":"pith:N6CLX3TT","schema_version":"1.0","canonical_sha256":"6f84bbee73057e6d13f5a65f444ffb09914386cfe1c5392da6522063a84d4986","source":{"kind":"arxiv","id":"2302.06834","version":1},"attestation_state":"computed","paper":{"title":"Improved Regret Bounds for Linear Adversarial MDPs via Linear Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Baoxiang Wang, Fang Kong, Shuai Li, Xiangcheng Zhang","submitted_at":"2023-02-14T05:15:23Z","abstract_excerpt":"Learning Markov decision processes (MDP) in an adversarial environment has been a challenging problem. The problem becomes even more challenging with function approximation, since the underlying structure of the loss function and transition kernel are especially hard to estimate in a varying environment. In fact, the state-of-the-art results for linear adversarial MDP achieve a regret of $\\tilde{O}(K^{6/7})$ ($K$ denotes the number of episodes), which admits a large room for improvement. In this paper, we investigate the problem with a new view, which reduces linear MDP into linear optimizatio"},"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":"2302.06834","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-14T05:15:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e8770a733aa4816bfab875f584c1852ffcfe81242f3a5b05925192a605c0b316","abstract_canon_sha256":"a6a2d7c0dd3d9dc6ec2b43970db58a647a54f978b787ad3ee782eb2cc1ee018b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:41:44.305702Z","signature_b64":"/3LMkefF1WgRvgPGtM8M8fOD2WGkxN+lq3xIlqumHvUbmpusynOEsFOrw7ujU+uEd9ncP3Hdb3a/nXJTzBXJBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6f84bbee73057e6d13f5a65f444ffb09914386cfe1c5392da6522063a84d4986","last_reissued_at":"2026-07-05T05:41:44.305169Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:41:44.305169Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improved Regret Bounds for Linear Adversarial MDPs via Linear Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Baoxiang Wang, Fang Kong, Shuai Li, Xiangcheng Zhang","submitted_at":"2023-02-14T05:15:23Z","abstract_excerpt":"Learning Markov decision processes (MDP) in an adversarial environment has been a challenging problem. The problem becomes even more challenging with function approximation, since the underlying structure of the loss function and transition kernel are especially hard to estimate in a varying environment. In fact, the state-of-the-art results for linear adversarial MDP achieve a regret of $\\tilde{O}(K^{6/7})$ ($K$ denotes the number of episodes), which admits a large room for improvement. In this paper, we investigate the problem with a new view, which reduces linear MDP into linear optimizatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.06834","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/2302.06834/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":"2302.06834","created_at":"2026-07-05T05:41:44.305234+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.06834v1","created_at":"2026-07-05T05:41:44.305234+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.06834","created_at":"2026-07-05T05:41:44.305234+00:00"},{"alias_kind":"pith_short_12","alias_value":"N6CLX3TTAV7G","created_at":"2026-07-05T05:41:44.305234+00:00"},{"alias_kind":"pith_short_16","alias_value":"N6CLX3TTAV7G2E7V","created_at":"2026-07-05T05:41:44.305234+00:00"},{"alias_kind":"pith_short_8","alias_value":"N6CLX3TT","created_at":"2026-07-05T05:41:44.305234+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/N6CLX3TTAV7G2E7VUZPUIT73BG","json":"https://pith.science/pith/N6CLX3TTAV7G2E7VUZPUIT73BG.json","graph_json":"https://pith.science/api/pith-number/N6CLX3TTAV7G2E7VUZPUIT73BG/graph.json","events_json":"https://pith.science/api/pith-number/N6CLX3TTAV7G2E7VUZPUIT73BG/events.json","paper":"https://pith.science/paper/N6CLX3TT"},"agent_actions":{"view_html":"https://pith.science/pith/N6CLX3TTAV7G2E7VUZPUIT73BG","download_json":"https://pith.science/pith/N6CLX3TTAV7G2E7VUZPUIT73BG.json","view_paper":"https://pith.science/paper/N6CLX3TT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.06834&json=true","fetch_graph":"https://pith.science/api/pith-number/N6CLX3TTAV7G2E7VUZPUIT73BG/graph.json","fetch_events":"https://pith.science/api/pith-number/N6CLX3TTAV7G2E7VUZPUIT73BG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N6CLX3TTAV7G2E7VUZPUIT73BG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N6CLX3TTAV7G2E7VUZPUIT73BG/action/storage_attestation","attest_author":"https://pith.science/pith/N6CLX3TTAV7G2E7VUZPUIT73BG/action/author_attestation","sign_citation":"https://pith.science/pith/N6CLX3TTAV7G2E7VUZPUIT73BG/action/citation_signature","submit_replication":"https://pith.science/pith/N6CLX3TTAV7G2E7VUZPUIT73BG/action/replication_record"}},"created_at":"2026-07-05T05:41:44.305234+00:00","updated_at":"2026-07-05T05:41:44.305234+00:00"}