{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:PQHVI7MQWYXD67AOPYHZDXLLKS","short_pith_number":"pith:PQHVI7MQ","schema_version":"1.0","canonical_sha256":"7c0f547d90b62e3f7c0e7e0f91dd6b54a720cabe8a343fa436b48baa596785d1","source":{"kind":"arxiv","id":"1706.04711","version":2},"attestation_state":"computed","paper":{"title":"Reinforcement Learning under Model Mismatch","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Aurko Roy, Huan Xu, Sebastian Pokutta","submitted_at":"2017-06-15T01:06:05Z","abstract_excerpt":"We study reinforcement learning under model misspecification, where we do not have access to the true environment but only to a reasonably close approximation to it. We address this problem by extending the framework of robust MDPs to the model-free Reinforcement Learning setting, where we do not have access to the model parameters, but can only sample states from it. We define robust versions of Q-learning, SARSA, and TD-learning and prove convergence to an approximately optimal robust policy and approximate value function respectively. We scale up the robust algorithms to large MDPs via func"},"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":"1706.04711","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-06-15T01:06:05Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"9927fe36aa2c89d1b3d483fe0f1dd57e2189130e1d96498f06c5ed02ae3ae963","abstract_canon_sha256":"2386781c533c02f8985c112fb5bd45503b4a5bd522ff5ac2200fa0207808e05e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:30:57.701903Z","signature_b64":"7UNn35Gk+YCLRt+8ziYiCu8UxNMP+ooruOvPlpT9uLkdhl8ykBIZYtP5q3yokRcu9eGDT0LY5DSSrDuMTHmHBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c0f547d90b62e3f7c0e7e0f91dd6b54a720cabe8a343fa436b48baa596785d1","last_reissued_at":"2026-05-18T00:30:57.701475Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:30:57.701475Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning under Model Mismatch","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Aurko Roy, Huan Xu, Sebastian Pokutta","submitted_at":"2017-06-15T01:06:05Z","abstract_excerpt":"We study reinforcement learning under model misspecification, where we do not have access to the true environment but only to a reasonably close approximation to it. We address this problem by extending the framework of robust MDPs to the model-free Reinforcement Learning setting, where we do not have access to the model parameters, but can only sample states from it. We define robust versions of Q-learning, SARSA, and TD-learning and prove convergence to an approximately optimal robust policy and approximate value function respectively. We scale up the robust algorithms to large MDPs via func"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.04711","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":""},"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":"1706.04711","created_at":"2026-05-18T00:30:57.701541+00:00"},{"alias_kind":"arxiv_version","alias_value":"1706.04711v2","created_at":"2026-05-18T00:30:57.701541+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.04711","created_at":"2026-05-18T00:30:57.701541+00:00"},{"alias_kind":"pith_short_12","alias_value":"PQHVI7MQWYXD","created_at":"2026-05-18T12:31:37.085036+00:00"},{"alias_kind":"pith_short_16","alias_value":"PQHVI7MQWYXD67AO","created_at":"2026-05-18T12:31:37.085036+00:00"},{"alias_kind":"pith_short_8","alias_value":"PQHVI7MQ","created_at":"2026-05-18T12:31:37.085036+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/PQHVI7MQWYXD67AOPYHZDXLLKS","json":"https://pith.science/pith/PQHVI7MQWYXD67AOPYHZDXLLKS.json","graph_json":"https://pith.science/api/pith-number/PQHVI7MQWYXD67AOPYHZDXLLKS/graph.json","events_json":"https://pith.science/api/pith-number/PQHVI7MQWYXD67AOPYHZDXLLKS/events.json","paper":"https://pith.science/paper/PQHVI7MQ"},"agent_actions":{"view_html":"https://pith.science/pith/PQHVI7MQWYXD67AOPYHZDXLLKS","download_json":"https://pith.science/pith/PQHVI7MQWYXD67AOPYHZDXLLKS.json","view_paper":"https://pith.science/paper/PQHVI7MQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1706.04711&json=true","fetch_graph":"https://pith.science/api/pith-number/PQHVI7MQWYXD67AOPYHZDXLLKS/graph.json","fetch_events":"https://pith.science/api/pith-number/PQHVI7MQWYXD67AOPYHZDXLLKS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PQHVI7MQWYXD67AOPYHZDXLLKS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PQHVI7MQWYXD67AOPYHZDXLLKS/action/storage_attestation","attest_author":"https://pith.science/pith/PQHVI7MQWYXD67AOPYHZDXLLKS/action/author_attestation","sign_citation":"https://pith.science/pith/PQHVI7MQWYXD67AOPYHZDXLLKS/action/citation_signature","submit_replication":"https://pith.science/pith/PQHVI7MQWYXD67AOPYHZDXLLKS/action/replication_record"}},"created_at":"2026-05-18T00:30:57.701541+00:00","updated_at":"2026-05-18T00:30:57.701541+00:00"}