{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:LECFQ2MHN37LLA2NMSM6ADHS2B","short_pith_number":"pith:LECFQ2MH","schema_version":"1.0","canonical_sha256":"59045869876efeb5834d6499e00cf2d05d07b2725be28cedf4dc2e1b19c141fa","source":{"kind":"arxiv","id":"2209.13841","version":1},"attestation_state":"computed","paper":{"title":"Online Policy Optimization for Robust MDP","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Baoxiang Wang, Jing Dong, Jingwei Li, Jingzhao Zhang","submitted_at":"2022-09-28T05:18:20Z","abstract_excerpt":"Reinforcement learning (RL) has exceeded human performance in many synthetic settings such as video games and Go. However, real-world deployment of end-to-end RL models is less common, as RL models can be very sensitive to slight perturbation of the environment. The robust Markov decision process (MDP) framework -- in which the transition probabilities belong to an uncertainty set around a nominal model -- provides one way to develop robust models. While previous analysis shows RL algorithms are effective assuming access to a generative model, it remains unclear whether RL can be efficient und"},"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":"2209.13841","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-28T05:18:20Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"4b0ba21f3ef5d1d7c01437c68755e618de73cf227ce3c04a130f248b543a1e65","abstract_canon_sha256":"fbb94cba0dc9caf630c22f5d2f913a37c78bd07947c33bbcaa2f02899bbd59d4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:01:44.818661Z","signature_b64":"FUtMReiaaqNyWxt8NGATv+C/FhVQv4WXeAb4Rd00CO/do/Cjc+9R/ydNpuAX4OuVgSCvKlkGmdLQX8Ssh0M9Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59045869876efeb5834d6499e00cf2d05d07b2725be28cedf4dc2e1b19c141fa","last_reissued_at":"2026-07-05T05:01:44.818172Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:01:44.818172Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Online Policy Optimization for Robust MDP","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Baoxiang Wang, Jing Dong, Jingwei Li, Jingzhao Zhang","submitted_at":"2022-09-28T05:18:20Z","abstract_excerpt":"Reinforcement learning (RL) has exceeded human performance in many synthetic settings such as video games and Go. However, real-world deployment of end-to-end RL models is less common, as RL models can be very sensitive to slight perturbation of the environment. The robust Markov decision process (MDP) framework -- in which the transition probabilities belong to an uncertainty set around a nominal model -- provides one way to develop robust models. While previous analysis shows RL algorithms are effective assuming access to a generative model, it remains unclear whether RL can be efficient und"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.13841","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/2209.13841/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":"2209.13841","created_at":"2026-07-05T05:01:44.818233+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.13841v1","created_at":"2026-07-05T05:01:44.818233+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.13841","created_at":"2026-07-05T05:01:44.818233+00:00"},{"alias_kind":"pith_short_12","alias_value":"LECFQ2MHN37L","created_at":"2026-07-05T05:01:44.818233+00:00"},{"alias_kind":"pith_short_16","alias_value":"LECFQ2MHN37LLA2N","created_at":"2026-07-05T05:01:44.818233+00:00"},{"alias_kind":"pith_short_8","alias_value":"LECFQ2MH","created_at":"2026-07-05T05:01:44.818233+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.24345","citing_title":"Evolving Robustness--Exploration Trade-off in Online Reinforcement Learning via Quantile Bayesian Risk MDPs","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LECFQ2MHN37LLA2NMSM6ADHS2B","json":"https://pith.science/pith/LECFQ2MHN37LLA2NMSM6ADHS2B.json","graph_json":"https://pith.science/api/pith-number/LECFQ2MHN37LLA2NMSM6ADHS2B/graph.json","events_json":"https://pith.science/api/pith-number/LECFQ2MHN37LLA2NMSM6ADHS2B/events.json","paper":"https://pith.science/paper/LECFQ2MH"},"agent_actions":{"view_html":"https://pith.science/pith/LECFQ2MHN37LLA2NMSM6ADHS2B","download_json":"https://pith.science/pith/LECFQ2MHN37LLA2NMSM6ADHS2B.json","view_paper":"https://pith.science/paper/LECFQ2MH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.13841&json=true","fetch_graph":"https://pith.science/api/pith-number/LECFQ2MHN37LLA2NMSM6ADHS2B/graph.json","fetch_events":"https://pith.science/api/pith-number/LECFQ2MHN37LLA2NMSM6ADHS2B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LECFQ2MHN37LLA2NMSM6ADHS2B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LECFQ2MHN37LLA2NMSM6ADHS2B/action/storage_attestation","attest_author":"https://pith.science/pith/LECFQ2MHN37LLA2NMSM6ADHS2B/action/author_attestation","sign_citation":"https://pith.science/pith/LECFQ2MHN37LLA2NMSM6ADHS2B/action/citation_signature","submit_replication":"https://pith.science/pith/LECFQ2MHN37LLA2NMSM6ADHS2B/action/replication_record"}},"created_at":"2026-07-05T05:01:44.818233+00:00","updated_at":"2026-07-05T05:01:44.818233+00:00"}