{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:PQHVI7MQWYXD67AOPYHZDXLLKS","short_pith_number":"pith:PQHVI7MQ","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"},"canonical_sha256":"7c0f547d90b62e3f7c0e7e0f91dd6b54a720cabe8a343fa436b48baa596785d1","source":{"kind":"arxiv","id":"1706.04711","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.04711","created_at":"2026-05-18T00:30:57Z"},{"alias_kind":"arxiv_version","alias_value":"1706.04711v2","created_at":"2026-05-18T00:30:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.04711","created_at":"2026-05-18T00:30:57Z"},{"alias_kind":"pith_short_12","alias_value":"PQHVI7MQWYXD","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_16","alias_value":"PQHVI7MQWYXD67AO","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_8","alias_value":"PQHVI7MQ","created_at":"2026-05-18T12:31:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:PQHVI7MQWYXD67AOPYHZDXLLKS","target":"record","payload":{"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"},"canonical_sha256":"7c0f547d90b62e3f7c0e7e0f91dd6b54a720cabe8a343fa436b48baa596785d1","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"},"source_kind":"arxiv","source_id":"1706.04711","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:30:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MGEHgURDLXBTfJy1GcCcJm0taLr1J6YAF+Fjx5zRP/2RpjHm67FLOjuREF21J0FNkj+jLo8bNJiqQ5ElZUYtDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T16:29:28.487697Z"},"content_sha256":"2101871582ea3bfbd18968ed369433adc3fdcc52b0df687f2fb1ab39d2eb457a","schema_version":"1.0","event_id":"sha256:2101871582ea3bfbd18968ed369433adc3fdcc52b0df687f2fb1ab39d2eb457a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:PQHVI7MQWYXD67AOPYHZDXLLKS","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:30:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vGQTJNps7vlGciwTjFr7dqwHWJL2Ap4Nfk4z/YNKGUOp2TWNV9nzcPf4WdPJOHrHgrNNYODII1ADJGMm3ejcDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T16:29:28.488040Z"},"content_sha256":"86b1d75aad3accba7df1d02e1b55a2a9149b1ffb060aa4ff4d11f23324f2f486","schema_version":"1.0","event_id":"sha256:86b1d75aad3accba7df1d02e1b55a2a9149b1ffb060aa4ff4d11f23324f2f486"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PQHVI7MQWYXD67AOPYHZDXLLKS/bundle.json","state_url":"https://pith.science/pith/PQHVI7MQWYXD67AOPYHZDXLLKS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PQHVI7MQWYXD67AOPYHZDXLLKS/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-19T16:29:28Z","links":{"resolver":"https://pith.science/pith/PQHVI7MQWYXD67AOPYHZDXLLKS","bundle":"https://pith.science/pith/PQHVI7MQWYXD67AOPYHZDXLLKS/bundle.json","state":"https://pith.science/pith/PQHVI7MQWYXD67AOPYHZDXLLKS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PQHVI7MQWYXD67AOPYHZDXLLKS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:PQHVI7MQWYXD67AOPYHZDXLLKS","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":"2386781c533c02f8985c112fb5bd45503b4a5bd522ff5ac2200fa0207808e05e","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-06-15T01:06:05Z","title_canon_sha256":"9927fe36aa2c89d1b3d483fe0f1dd57e2189130e1d96498f06c5ed02ae3ae963"},"schema_version":"1.0","source":{"id":"1706.04711","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.04711","created_at":"2026-05-18T00:30:57Z"},{"alias_kind":"arxiv_version","alias_value":"1706.04711v2","created_at":"2026-05-18T00:30:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.04711","created_at":"2026-05-18T00:30:57Z"},{"alias_kind":"pith_short_12","alias_value":"PQHVI7MQWYXD","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_16","alias_value":"PQHVI7MQWYXD67AO","created_at":"2026-05-18T12:31:37Z"},{"alias_kind":"pith_short_8","alias_value":"PQHVI7MQ","created_at":"2026-05-18T12:31:37Z"}],"graph_snapshots":[{"event_id":"sha256:86b1d75aad3accba7df1d02e1b55a2a9149b1ffb060aa4ff4d11f23324f2f486","target":"graph","created_at":"2026-05-18T00:30:57Z","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"},"paper":{"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","authors_text":"Aurko Roy, Huan Xu, Sebastian Pokutta","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-06-15T01:06:05Z","title":"Reinforcement Learning under Model Mismatch"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.04711","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":"sha256:2101871582ea3bfbd18968ed369433adc3fdcc52b0df687f2fb1ab39d2eb457a","target":"record","created_at":"2026-05-18T00:30:57Z","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":"2386781c533c02f8985c112fb5bd45503b4a5bd522ff5ac2200fa0207808e05e","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-06-15T01:06:05Z","title_canon_sha256":"9927fe36aa2c89d1b3d483fe0f1dd57e2189130e1d96498f06c5ed02ae3ae963"},"schema_version":"1.0","source":{"id":"1706.04711","kind":"arxiv","version":2}},"canonical_sha256":"7c0f547d90b62e3f7c0e7e0f91dd6b54a720cabe8a343fa436b48baa596785d1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7c0f547d90b62e3f7c0e7e0f91dd6b54a720cabe8a343fa436b48baa596785d1","first_computed_at":"2026-05-18T00:30:57.701475Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:30:57.701475Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7UNn35Gk+YCLRt+8ziYiCu8UxNMP+ooruOvPlpT9uLkdhl8ykBIZYtP5q3yokRcu9eGDT0LY5DSSrDuMTHmHBg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:30:57.701903Z","signed_message":"canonical_sha256_bytes"},"source_id":"1706.04711","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2101871582ea3bfbd18968ed369433adc3fdcc52b0df687f2fb1ab39d2eb457a","sha256:86b1d75aad3accba7df1d02e1b55a2a9149b1ffb060aa4ff4d11f23324f2f486"],"state_sha256":"7d31f53d7c6392759f17a6bb93f78e3686580d3351a659a21c45bfdc290b4487"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GqGhj0G6o9aeyzZVSBo7+TOgYmFNfLK6Yn4YwURTb8r+65mKkYxXEZLRv95JbnvrClFdcHVeFA0KkPUB6H+2BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-19T16:29:28.490026Z","bundle_sha256":"dcd1b11e903d15d361de7783a99b58036f0cebb3ed973fd6a27d24fa21a66ae4"}}