{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:PN4NJSQZO5UXMJPU62OFNDBYCP","short_pith_number":"pith:PN4NJSQZ","schema_version":"1.0","canonical_sha256":"7b78d4ca1977697625f4f69c568c3813cb11865c00342ef90d5837319bf14df2","source":{"kind":"arxiv","id":"1904.08361","version":1},"attestation_state":"computed","paper":{"title":"Decoupled Data Based Approach for Learning to Control Nonlinear Dynamical Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO","cs.SY","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dan Yu, Dileep Kalathil, Karthikeya Parunandi, Ran Wang, Suman Chakravorty","submitted_at":"2019-04-17T16:58:18Z","abstract_excerpt":"This paper addresses the problem of learning the optimal control policy for a nonlinear stochastic dynamical system with continuous state space, continuous action space and unknown dynamics. This class of problems are typically addressed in stochastic adaptive control and reinforcement learning literature using model-based and model-free approaches respectively. Both methods rely on solving a dynamic programming problem, either directly or indirectly, for finding the optimal closed loop control policy. The inherent `curse of dimensionality' associated with dynamic programming method makes thes"},"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":"1904.08361","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-17T16:58:18Z","cross_cats_sorted":["cs.RO","cs.SY","stat.ML"],"title_canon_sha256":"7abcc39441e1b974f69ed64757befffe835fa7cb94eb954fc1a7fa32916b1cdd","abstract_canon_sha256":"b0b342fd1c8c186faa64a29779b158de2f7d4799a87942c61794bd1703f9f6f9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:48:17.899770Z","signature_b64":"ekEJVn3qRTBiGpx38KrvliaZyzz/mcuMXnSJNeUG18FF42xEgr9WosM7tmZV+wxVmKt7yjqbspF5efBbrt6zAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b78d4ca1977697625f4f69c568c3813cb11865c00342ef90d5837319bf14df2","last_reissued_at":"2026-05-17T23:48:17.899077Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:48:17.899077Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Decoupled Data Based Approach for Learning to Control Nonlinear Dynamical Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO","cs.SY","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dan Yu, Dileep Kalathil, Karthikeya Parunandi, Ran Wang, Suman Chakravorty","submitted_at":"2019-04-17T16:58:18Z","abstract_excerpt":"This paper addresses the problem of learning the optimal control policy for a nonlinear stochastic dynamical system with continuous state space, continuous action space and unknown dynamics. This class of problems are typically addressed in stochastic adaptive control and reinforcement learning literature using model-based and model-free approaches respectively. Both methods rely on solving a dynamic programming problem, either directly or indirectly, for finding the optimal closed loop control policy. The inherent `curse of dimensionality' associated with dynamic programming method makes thes"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.08361","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":"1904.08361","created_at":"2026-05-17T23:48:17.899178+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.08361v1","created_at":"2026-05-17T23:48:17.899178+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.08361","created_at":"2026-05-17T23:48:17.899178+00:00"},{"alias_kind":"pith_short_12","alias_value":"PN4NJSQZO5UX","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_16","alias_value":"PN4NJSQZO5UXMJPU","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_8","alias_value":"PN4NJSQZ","created_at":"2026-05-18T12:33:24.271573+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/PN4NJSQZO5UXMJPU62OFNDBYCP","json":"https://pith.science/pith/PN4NJSQZO5UXMJPU62OFNDBYCP.json","graph_json":"https://pith.science/api/pith-number/PN4NJSQZO5UXMJPU62OFNDBYCP/graph.json","events_json":"https://pith.science/api/pith-number/PN4NJSQZO5UXMJPU62OFNDBYCP/events.json","paper":"https://pith.science/paper/PN4NJSQZ"},"agent_actions":{"view_html":"https://pith.science/pith/PN4NJSQZO5UXMJPU62OFNDBYCP","download_json":"https://pith.science/pith/PN4NJSQZO5UXMJPU62OFNDBYCP.json","view_paper":"https://pith.science/paper/PN4NJSQZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.08361&json=true","fetch_graph":"https://pith.science/api/pith-number/PN4NJSQZO5UXMJPU62OFNDBYCP/graph.json","fetch_events":"https://pith.science/api/pith-number/PN4NJSQZO5UXMJPU62OFNDBYCP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PN4NJSQZO5UXMJPU62OFNDBYCP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PN4NJSQZO5UXMJPU62OFNDBYCP/action/storage_attestation","attest_author":"https://pith.science/pith/PN4NJSQZO5UXMJPU62OFNDBYCP/action/author_attestation","sign_citation":"https://pith.science/pith/PN4NJSQZO5UXMJPU62OFNDBYCP/action/citation_signature","submit_replication":"https://pith.science/pith/PN4NJSQZO5UXMJPU62OFNDBYCP/action/replication_record"}},"created_at":"2026-05-17T23:48:17.899178+00:00","updated_at":"2026-05-17T23:48:17.899178+00:00"}