{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2013:IMK7TAMPWUHI55BQOPE7MLTVK7","short_pith_number":"pith:IMK7TAMP","canonical_record":{"source":{"id":"1311.6107","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2013-11-24T11:26:07Z","cross_cats_sorted":["cs.LG","math.OC","stat.ML"],"title_canon_sha256":"2af7bf1fff8478465099a8ceeafb121f618e0e6a856ca4c028915ed517a86110","abstract_canon_sha256":"b564f8501d4b85388c582f4960f5d3a5938c0eb742c9f97514d7ade109e4bf0e"},"schema_version":"1.0"},"canonical_sha256":"4315f9818fb50e8ef43073c9f62e7557cc379ca827411513498ecaead5e45fef","source":{"kind":"arxiv","id":"1311.6107","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1311.6107","created_at":"2026-05-18T02:52:12Z"},{"alias_kind":"arxiv_version","alias_value":"1311.6107v3","created_at":"2026-05-18T02:52:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1311.6107","created_at":"2026-05-18T02:52:12Z"},{"alias_kind":"pith_short_12","alias_value":"IMK7TAMPWUHI","created_at":"2026-05-18T12:27:46Z"},{"alias_kind":"pith_short_16","alias_value":"IMK7TAMPWUHI55BQ","created_at":"2026-05-18T12:27:46Z"},{"alias_kind":"pith_short_8","alias_value":"IMK7TAMP","created_at":"2026-05-18T12:27:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2013:IMK7TAMPWUHI55BQOPE7MLTVK7","target":"record","payload":{"canonical_record":{"source":{"id":"1311.6107","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2013-11-24T11:26:07Z","cross_cats_sorted":["cs.LG","math.OC","stat.ML"],"title_canon_sha256":"2af7bf1fff8478465099a8ceeafb121f618e0e6a856ca4c028915ed517a86110","abstract_canon_sha256":"b564f8501d4b85388c582f4960f5d3a5938c0eb742c9f97514d7ade109e4bf0e"},"schema_version":"1.0"},"canonical_sha256":"4315f9818fb50e8ef43073c9f62e7557cc379ca827411513498ecaead5e45fef","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:52:12.267235Z","signature_b64":"jxWCuq8croN4slpjOHA0oYSLJS5DCR3iZ+GTV/ozYFWvfWxhf83Wlfk03jleBn3nE8IipStDWEqJ9A5amu2vDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4315f9818fb50e8ef43073c9f62e7557cc379ca827411513498ecaead5e45fef","last_reissued_at":"2026-05-18T02:52:12.266549Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:52:12.266549Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1311.6107","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:52:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Hc2VfEeJc19OqFapHdbgArzB+6QmSv/0nOLPxPEWIjvg36PK1v0do7q61EO+SASHgoSMA2GsfnMZDO0RSOpwDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T11:32:20.003524Z"},"content_sha256":"1dcde929646a89aeba73731067d4ab0a86cd6311ac602507567d1fc659b2f328","schema_version":"1.0","event_id":"sha256:1dcde929646a89aeba73731067d4ab0a86cd6311ac602507567d1fc659b2f328"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2013:IMK7TAMPWUHI55BQOPE7MLTVK7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Off-policy reinforcement learning for $ H_\\infty $ control design","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC","stat.ML"],"primary_cat":"cs.SY","authors_text":"Biao Luo, Huai-Ning Wu, Tingwen Huang","submitted_at":"2013-11-24T11:26:07Z","abstract_excerpt":"The $H_\\infty$ control design problem is considered for nonlinear systems with unknown internal system model. It is known that the nonlinear $ H_\\infty $ control problem can be transformed into solving the so-called Hamilton-Jacobi-Isaacs (HJI) equation, which is a nonlinear partial differential equation that is generally impossible to be solved analytically. Even worse, model-based approaches cannot be used for approximately solving HJI equation, when the accurate system model is unavailable or costly to obtain in practice. To overcome these difficulties, an off-policy reinforcement leaning ("},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1311.6107","kind":"arxiv","version":3},"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":"2026-05-18T02:52:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VaSPk406vExsU25rc2EE4Y6X0t541cU7CCyMaKIOhTRz92mTMjWCajRukPgm9E/Fr7gVL6Ba853nSESkBCvaBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T11:32:20.004205Z"},"content_sha256":"10b7e670e3f5a6bdbdfd10e1102de84bf49b58efd9adeae7a6aeb1008590f990","schema_version":"1.0","event_id":"sha256:10b7e670e3f5a6bdbdfd10e1102de84bf49b58efd9adeae7a6aeb1008590f990"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IMK7TAMPWUHI55BQOPE7MLTVK7/bundle.json","state_url":"https://pith.science/pith/IMK7TAMPWUHI55BQOPE7MLTVK7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IMK7TAMPWUHI55BQOPE7MLTVK7/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":"2026-06-09T11:32:20Z","links":{"resolver":"https://pith.science/pith/IMK7TAMPWUHI55BQOPE7MLTVK7","bundle":"https://pith.science/pith/IMK7TAMPWUHI55BQOPE7MLTVK7/bundle.json","state":"https://pith.science/pith/IMK7TAMPWUHI55BQOPE7MLTVK7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IMK7TAMPWUHI55BQOPE7MLTVK7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2013:IMK7TAMPWUHI55BQOPE7MLTVK7","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":"b564f8501d4b85388c582f4960f5d3a5938c0eb742c9f97514d7ade109e4bf0e","cross_cats_sorted":["cs.LG","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2013-11-24T11:26:07Z","title_canon_sha256":"2af7bf1fff8478465099a8ceeafb121f618e0e6a856ca4c028915ed517a86110"},"schema_version":"1.0","source":{"id":"1311.6107","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1311.6107","created_at":"2026-05-18T02:52:12Z"},{"alias_kind":"arxiv_version","alias_value":"1311.6107v3","created_at":"2026-05-18T02:52:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1311.6107","created_at":"2026-05-18T02:52:12Z"},{"alias_kind":"pith_short_12","alias_value":"IMK7TAMPWUHI","created_at":"2026-05-18T12:27:46Z"},{"alias_kind":"pith_short_16","alias_value":"IMK7TAMPWUHI55BQ","created_at":"2026-05-18T12:27:46Z"},{"alias_kind":"pith_short_8","alias_value":"IMK7TAMP","created_at":"2026-05-18T12:27:46Z"}],"graph_snapshots":[{"event_id":"sha256:10b7e670e3f5a6bdbdfd10e1102de84bf49b58efd9adeae7a6aeb1008590f990","target":"graph","created_at":"2026-05-18T02:52:12Z","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":"The $H_\\infty$ control design problem is considered for nonlinear systems with unknown internal system model. It is known that the nonlinear $ H_\\infty $ control problem can be transformed into solving the so-called Hamilton-Jacobi-Isaacs (HJI) equation, which is a nonlinear partial differential equation that is generally impossible to be solved analytically. Even worse, model-based approaches cannot be used for approximately solving HJI equation, when the accurate system model is unavailable or costly to obtain in practice. To overcome these difficulties, an off-policy reinforcement leaning (","authors_text":"Biao Luo, Huai-Ning Wu, Tingwen Huang","cross_cats":["cs.LG","math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2013-11-24T11:26:07Z","title":"Off-policy reinforcement learning for $ H_\\infty $ control design"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1311.6107","kind":"arxiv","version":3},"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":"sha256:1dcde929646a89aeba73731067d4ab0a86cd6311ac602507567d1fc659b2f328","target":"record","created_at":"2026-05-18T02:52:12Z","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":"b564f8501d4b85388c582f4960f5d3a5938c0eb742c9f97514d7ade109e4bf0e","cross_cats_sorted":["cs.LG","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SY","submitted_at":"2013-11-24T11:26:07Z","title_canon_sha256":"2af7bf1fff8478465099a8ceeafb121f618e0e6a856ca4c028915ed517a86110"},"schema_version":"1.0","source":{"id":"1311.6107","kind":"arxiv","version":3}},"canonical_sha256":"4315f9818fb50e8ef43073c9f62e7557cc379ca827411513498ecaead5e45fef","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4315f9818fb50e8ef43073c9f62e7557cc379ca827411513498ecaead5e45fef","first_computed_at":"2026-05-18T02:52:12.266549Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:52:12.266549Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jxWCuq8croN4slpjOHA0oYSLJS5DCR3iZ+GTV/ozYFWvfWxhf83Wlfk03jleBn3nE8IipStDWEqJ9A5amu2vDA==","signature_status":"signed_v1","signed_at":"2026-05-18T02:52:12.267235Z","signed_message":"canonical_sha256_bytes"},"source_id":"1311.6107","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1dcde929646a89aeba73731067d4ab0a86cd6311ac602507567d1fc659b2f328","sha256:10b7e670e3f5a6bdbdfd10e1102de84bf49b58efd9adeae7a6aeb1008590f990"],"state_sha256":"89f73d85a3ea2fb69c97f65e52b9e84262a153dc38fefaf9fe8088d631c901d2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B4ZJtsF+e6YXvddrPdlTdzuF12rauWSZVmQJGmcUZJKdtrH6NjZ4nbharYJ1csfRc/BTUxbfzU1gJp9lA+wNBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T11:32:20.007650Z","bundle_sha256":"bced1b3a697049e195aa5ea9db506d781b6dcf79103dabf64e2725f9dc8b299e"}}