{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:TOZERWOVYNT7JQQVEA63IQLVH5","short_pith_number":"pith:TOZERWOV","schema_version":"1.0","canonical_sha256":"9bb248d9d5c367f4c215203db441753f74805ab2ef88ed47c2436323a2ed8923","source":{"kind":"arxiv","id":"1905.10649","version":1},"attestation_state":"computed","paper":{"title":"Large Scale Markov Decision Processes with Changing Rewards","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Adrian Rivera Cardoso, He Wang, Huan Xu","submitted_at":"2019-05-25T18:26:49Z","abstract_excerpt":"We consider Markov Decision Processes (MDPs) where the rewards are unknown and may change in an adversarial manner. We provide an algorithm that achieves state-of-the-art regret bound of $O( \\sqrt{\\tau (\\ln|S|+\\ln|A|)T}\\ln(T))$, where $S$ is the state space, $A$ is the action space, $\\tau$ is the mixing time of the MDP, and $T$ is the number of periods. The algorithm's computational complexity is polynomial in $|S|$ and $|A|$ per period. We then consider a setting often encountered in practice, where the state space of the MDP is too large to allow for exact solutions. By approximating the sta"},"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":"1905.10649","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-25T18:26:49Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"1eb438c545506b0d1e10c74fe85ce85ed82d151fe4e9981bcc5f54164aefc697","abstract_canon_sha256":"b85de7141697fb7ea9058960f6d79748d39014b2225ec952974704b2b2c7af73"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:05.688714Z","signature_b64":"//ae+Bo2ksmRG/lDQ5BZehPiBjDp0npSUny9nhBqBLQSoN0v7a72g3QMcdjZRRoJyi87dy71tvRIcghhzJM4Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9bb248d9d5c367f4c215203db441753f74805ab2ef88ed47c2436323a2ed8923","last_reissued_at":"2026-05-17T23:45:05.687998Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:05.687998Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Scale Markov Decision Processes with Changing Rewards","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Adrian Rivera Cardoso, He Wang, Huan Xu","submitted_at":"2019-05-25T18:26:49Z","abstract_excerpt":"We consider Markov Decision Processes (MDPs) where the rewards are unknown and may change in an adversarial manner. We provide an algorithm that achieves state-of-the-art regret bound of $O( \\sqrt{\\tau (\\ln|S|+\\ln|A|)T}\\ln(T))$, where $S$ is the state space, $A$ is the action space, $\\tau$ is the mixing time of the MDP, and $T$ is the number of periods. The algorithm's computational complexity is polynomial in $|S|$ and $|A|$ per period. We then consider a setting often encountered in practice, where the state space of the MDP is too large to allow for exact solutions. By approximating the sta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.10649","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":""},"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":"1905.10649","created_at":"2026-05-17T23:45:05.688104+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.10649v1","created_at":"2026-05-17T23:45:05.688104+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.10649","created_at":"2026-05-17T23:45:05.688104+00:00"},{"alias_kind":"pith_short_12","alias_value":"TOZERWOVYNT7","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"TOZERWOVYNT7JQQV","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"TOZERWOV","created_at":"2026-05-18T12:33:30.264802+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/TOZERWOVYNT7JQQVEA63IQLVH5","json":"https://pith.science/pith/TOZERWOVYNT7JQQVEA63IQLVH5.json","graph_json":"https://pith.science/api/pith-number/TOZERWOVYNT7JQQVEA63IQLVH5/graph.json","events_json":"https://pith.science/api/pith-number/TOZERWOVYNT7JQQVEA63IQLVH5/events.json","paper":"https://pith.science/paper/TOZERWOV"},"agent_actions":{"view_html":"https://pith.science/pith/TOZERWOVYNT7JQQVEA63IQLVH5","download_json":"https://pith.science/pith/TOZERWOVYNT7JQQVEA63IQLVH5.json","view_paper":"https://pith.science/paper/TOZERWOV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.10649&json=true","fetch_graph":"https://pith.science/api/pith-number/TOZERWOVYNT7JQQVEA63IQLVH5/graph.json","fetch_events":"https://pith.science/api/pith-number/TOZERWOVYNT7JQQVEA63IQLVH5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TOZERWOVYNT7JQQVEA63IQLVH5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TOZERWOVYNT7JQQVEA63IQLVH5/action/storage_attestation","attest_author":"https://pith.science/pith/TOZERWOVYNT7JQQVEA63IQLVH5/action/author_attestation","sign_citation":"https://pith.science/pith/TOZERWOVYNT7JQQVEA63IQLVH5/action/citation_signature","submit_replication":"https://pith.science/pith/TOZERWOVYNT7JQQVEA63IQLVH5/action/replication_record"}},"created_at":"2026-05-17T23:45:05.688104+00:00","updated_at":"2026-05-17T23:45:05.688104+00:00"}