{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:PJ7HTIVYV2FTRW3JYOVES3BRHO","short_pith_number":"pith:PJ7HTIVY","schema_version":"1.0","canonical_sha256":"7a7e79a2b8ae8b38db69c3aa496c313bb699bc56bb65bfec8a1d6e0cf8fdd91e","source":{"kind":"arxiv","id":"2602.09474","version":2},"attestation_state":"computed","paper":{"title":"Online Learning in MDPs with Partially Adversarial Transitions and Losses","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ofir Schlisselberg, Tal Lancewicki, Yishay Mansour","submitted_at":"2026-02-10T07:13:11Z","abstract_excerpt":"We study reinforcement learning in MDPs whose transition function is stochastic at most steps but may behave adversarially at a fixed subset of $\\Lambda$ steps per episode. This model captures environments that are stable except at a few vulnerable points. We introduce \\emph{conditioned occupancy measures}, which remain stable across episodes even with adversarial transitions, and use them to design two algorithms. The first handles arbitrary adversarial steps and achieves regret $\\tilde{O}(H S^{\\Lambda}\\sqrt{K S A^{\\Lambda+1}})$, where $K$ is the number of episodes, $S$ is the number of state"},"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":"2602.09474","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-02-10T07:13:11Z","cross_cats_sorted":[],"title_canon_sha256":"448e5f1d90c895d695da52110a7b00f361839efd21d81c472ba2d34401a10467","abstract_canon_sha256":"02d8e4d32ebd602fb66b1b84c0e72e4d4925e94fd6fd3d4e63da3f2a37369764"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:51.201853Z","signature_b64":"CR1srPJADyi4/FJb1ucY3AvjvpK7eCfvcPy+ZHsKj37WCyDTLDuMzaePcvqHbnWwb+s5xuBU/QfC7cR5jTNyBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a7e79a2b8ae8b38db69c3aa496c313bb699bc56bb65bfec8a1d6e0cf8fdd91e","last_reissued_at":"2026-06-02T02:04:51.201416Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:51.201416Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Online Learning in MDPs with Partially Adversarial Transitions and Losses","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ofir Schlisselberg, Tal Lancewicki, Yishay Mansour","submitted_at":"2026-02-10T07:13:11Z","abstract_excerpt":"We study reinforcement learning in MDPs whose transition function is stochastic at most steps but may behave adversarially at a fixed subset of $\\Lambda$ steps per episode. This model captures environments that are stable except at a few vulnerable points. We introduce \\emph{conditioned occupancy measures}, which remain stable across episodes even with adversarial transitions, and use them to design two algorithms. The first handles arbitrary adversarial steps and achieves regret $\\tilde{O}(H S^{\\Lambda}\\sqrt{K S A^{\\Lambda+1}})$, where $K$ is the number of episodes, $S$ is the number of state"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.09474","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/2602.09474/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":"2602.09474","created_at":"2026-06-02T02:04:51.201472+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.09474v2","created_at":"2026-06-02T02:04:51.201472+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.09474","created_at":"2026-06-02T02:04:51.201472+00:00"},{"alias_kind":"pith_short_12","alias_value":"PJ7HTIVYV2FT","created_at":"2026-06-02T02:04:51.201472+00:00"},{"alias_kind":"pith_short_16","alias_value":"PJ7HTIVYV2FTRW3J","created_at":"2026-06-02T02:04:51.201472+00:00"},{"alias_kind":"pith_short_8","alias_value":"PJ7HTIVY","created_at":"2026-06-02T02:04:51.201472+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/PJ7HTIVYV2FTRW3JYOVES3BRHO","json":"https://pith.science/pith/PJ7HTIVYV2FTRW3JYOVES3BRHO.json","graph_json":"https://pith.science/api/pith-number/PJ7HTIVYV2FTRW3JYOVES3BRHO/graph.json","events_json":"https://pith.science/api/pith-number/PJ7HTIVYV2FTRW3JYOVES3BRHO/events.json","paper":"https://pith.science/paper/PJ7HTIVY"},"agent_actions":{"view_html":"https://pith.science/pith/PJ7HTIVYV2FTRW3JYOVES3BRHO","download_json":"https://pith.science/pith/PJ7HTIVYV2FTRW3JYOVES3BRHO.json","view_paper":"https://pith.science/paper/PJ7HTIVY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.09474&json=true","fetch_graph":"https://pith.science/api/pith-number/PJ7HTIVYV2FTRW3JYOVES3BRHO/graph.json","fetch_events":"https://pith.science/api/pith-number/PJ7HTIVYV2FTRW3JYOVES3BRHO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PJ7HTIVYV2FTRW3JYOVES3BRHO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PJ7HTIVYV2FTRW3JYOVES3BRHO/action/storage_attestation","attest_author":"https://pith.science/pith/PJ7HTIVYV2FTRW3JYOVES3BRHO/action/author_attestation","sign_citation":"https://pith.science/pith/PJ7HTIVYV2FTRW3JYOVES3BRHO/action/citation_signature","submit_replication":"https://pith.science/pith/PJ7HTIVYV2FTRW3JYOVES3BRHO/action/replication_record"}},"created_at":"2026-06-02T02:04:51.201472+00:00","updated_at":"2026-06-02T02:04:51.201472+00:00"}