{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:YLBAURM3PDGJVTL2T3P6LI5ZWP","short_pith_number":"pith:YLBAURM3","schema_version":"1.0","canonical_sha256":"c2c20a459b78cc9acd7a9edfe5a3b9b3d1c0bcbc05e4721807a83dbdcea88ec1","source":{"kind":"arxiv","id":"2102.08940","version":2},"attestation_state":"computed","paper":{"title":"Near-optimal Policy Optimization Algorithms for Learning Adversarial Linear Mixture MDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dongruo Zhou, Jiafan He, Quanquan Gu","submitted_at":"2021-02-17T18:54:08Z","abstract_excerpt":"Learning Markov decision processes (MDPs) in the presence of the adversary is a challenging problem in reinforcement learning (RL). In this paper, we study RL in episodic MDPs with adversarial reward and full information feedback, where the unknown transition probability function is a linear function of a given feature mapping, and the reward function can change arbitrarily episode by episode. We propose an optimistic policy optimization algorithm POWERS and show that it can achieve $\\tilde{O}(dH\\sqrt{T})$ regret, where $H$ is the length of the episode, $T$ is the number of interactions with t"},"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":"2102.08940","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-17T18:54:08Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"722bc4f870f096e7c40cf5b9419f2b82ed78a674fe1e23ae024476eae7fde45b","abstract_canon_sha256":"86b9f3dec1d5ab584d21831952fe80e970b0dbcda90aeb767cafeee49c090be5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:16:11.782301Z","signature_b64":"Jioowfb7rdc8iERRB8aTZ8s8zgVDUCNkQpgGOdwqi6/NpcHmRql584rxH/N/NO+sI0VaJNb40WMA3ps3JYCnCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c2c20a459b78cc9acd7a9edfe5a3b9b3d1c0bcbc05e4721807a83dbdcea88ec1","last_reissued_at":"2026-07-05T04:16:11.781913Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:16:11.781913Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Near-optimal Policy Optimization Algorithms for Learning Adversarial Linear Mixture MDPs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dongruo Zhou, Jiafan He, Quanquan Gu","submitted_at":"2021-02-17T18:54:08Z","abstract_excerpt":"Learning Markov decision processes (MDPs) in the presence of the adversary is a challenging problem in reinforcement learning (RL). In this paper, we study RL in episodic MDPs with adversarial reward and full information feedback, where the unknown transition probability function is a linear function of a given feature mapping, and the reward function can change arbitrarily episode by episode. We propose an optimistic policy optimization algorithm POWERS and show that it can achieve $\\tilde{O}(dH\\sqrt{T})$ regret, where $H$ is the length of the episode, $T$ is the number of interactions with t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.08940","kind":"arxiv","version":2},"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/2102.08940/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":"2102.08940","created_at":"2026-07-05T04:16:11.781978+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.08940v2","created_at":"2026-07-05T04:16:11.781978+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.08940","created_at":"2026-07-05T04:16:11.781978+00:00"},{"alias_kind":"pith_short_12","alias_value":"YLBAURM3PDGJ","created_at":"2026-07-05T04:16:11.781978+00:00"},{"alias_kind":"pith_short_16","alias_value":"YLBAURM3PDGJVTL2","created_at":"2026-07-05T04:16:11.781978+00:00"},{"alias_kind":"pith_short_8","alias_value":"YLBAURM3","created_at":"2026-07-05T04:16:11.781978+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/YLBAURM3PDGJVTL2T3P6LI5ZWP","json":"https://pith.science/pith/YLBAURM3PDGJVTL2T3P6LI5ZWP.json","graph_json":"https://pith.science/api/pith-number/YLBAURM3PDGJVTL2T3P6LI5ZWP/graph.json","events_json":"https://pith.science/api/pith-number/YLBAURM3PDGJVTL2T3P6LI5ZWP/events.json","paper":"https://pith.science/paper/YLBAURM3"},"agent_actions":{"view_html":"https://pith.science/pith/YLBAURM3PDGJVTL2T3P6LI5ZWP","download_json":"https://pith.science/pith/YLBAURM3PDGJVTL2T3P6LI5ZWP.json","view_paper":"https://pith.science/paper/YLBAURM3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.08940&json=true","fetch_graph":"https://pith.science/api/pith-number/YLBAURM3PDGJVTL2T3P6LI5ZWP/graph.json","fetch_events":"https://pith.science/api/pith-number/YLBAURM3PDGJVTL2T3P6LI5ZWP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YLBAURM3PDGJVTL2T3P6LI5ZWP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YLBAURM3PDGJVTL2T3P6LI5ZWP/action/storage_attestation","attest_author":"https://pith.science/pith/YLBAURM3PDGJVTL2T3P6LI5ZWP/action/author_attestation","sign_citation":"https://pith.science/pith/YLBAURM3PDGJVTL2T3P6LI5ZWP/action/citation_signature","submit_replication":"https://pith.science/pith/YLBAURM3PDGJVTL2T3P6LI5ZWP/action/replication_record"}},"created_at":"2026-07-05T04:16:11.781978+00:00","updated_at":"2026-07-05T04:16:11.781978+00:00"}