{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:YLBAURM3PDGJVTL2T3P6LI5ZWP","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":"86b9f3dec1d5ab584d21831952fe80e970b0dbcda90aeb767cafeee49c090be5","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-17T18:54:08Z","title_canon_sha256":"722bc4f870f096e7c40cf5b9419f2b82ed78a674fe1e23ae024476eae7fde45b"},"schema_version":"1.0","source":{"id":"2102.08940","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.08940","created_at":"2026-07-05T04:16:11Z"},{"alias_kind":"arxiv_version","alias_value":"2102.08940v2","created_at":"2026-07-05T04:16:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.08940","created_at":"2026-07-05T04:16:11Z"},{"alias_kind":"pith_short_12","alias_value":"YLBAURM3PDGJ","created_at":"2026-07-05T04:16:11Z"},{"alias_kind":"pith_short_16","alias_value":"YLBAURM3PDGJVTL2","created_at":"2026-07-05T04:16:11Z"},{"alias_kind":"pith_short_8","alias_value":"YLBAURM3","created_at":"2026-07-05T04:16:11Z"}],"graph_snapshots":[{"event_id":"sha256:0a469fde197b6a9c126935dba984fc645e0bf22a0c4db8f64b80d8f0608d0158","target":"graph","created_at":"2026-07-05T04:16:11Z","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/2102.08940/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Dongruo Zhou, Jiafan He, Quanquan Gu","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-17T18:54:08Z","title":"Near-optimal Policy Optimization Algorithms for Learning Adversarial Linear Mixture MDPs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.08940","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":"sha256:40dc1fb4ab3b7c8347035f339c153763ed027a5182f193698212aeb336482f2f","target":"record","created_at":"2026-07-05T04:16:11Z","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":"86b9f3dec1d5ab584d21831952fe80e970b0dbcda90aeb767cafeee49c090be5","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-17T18:54:08Z","title_canon_sha256":"722bc4f870f096e7c40cf5b9419f2b82ed78a674fe1e23ae024476eae7fde45b"},"schema_version":"1.0","source":{"id":"2102.08940","kind":"arxiv","version":2}},"canonical_sha256":"c2c20a459b78cc9acd7a9edfe5a3b9b3d1c0bcbc05e4721807a83dbdcea88ec1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c2c20a459b78cc9acd7a9edfe5a3b9b3d1c0bcbc05e4721807a83dbdcea88ec1","first_computed_at":"2026-07-05T04:16:11.781913Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:16:11.781913Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Jioowfb7rdc8iERRB8aTZ8s8zgVDUCNkQpgGOdwqi6/NpcHmRql584rxH/N/NO+sI0VaJNb40WMA3ps3JYCnCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:16:11.782301Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.08940","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:40dc1fb4ab3b7c8347035f339c153763ed027a5182f193698212aeb336482f2f","sha256:0a469fde197b6a9c126935dba984fc645e0bf22a0c4db8f64b80d8f0608d0158"],"state_sha256":"a27b908f691b8c2b8f782ac14031b1f85376a2ce6736c8898615e3dbfb85db86"}