{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:IKI2OWAUFXXISALBNTFIQPUISN","short_pith_number":"pith:IKI2OWAU","canonical_record":{"source":{"id":"1803.07743","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2018-03-21T04:16:14Z","cross_cats_sorted":[],"title_canon_sha256":"4ce349c6b4e8c3fa02991827d17c51189d7ab1b5f882054993f45b5ac0e20eff","abstract_canon_sha256":"dd80f0fc087ff25bd94965e371dd92b8047de264fe6bb00157b18505db5d886e"},"schema_version":"1.0"},"canonical_sha256":"4291a758142dee8901616cca883e88934ceecb34e469980be48605977a6b88c1","source":{"kind":"arxiv","id":"1803.07743","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.07743","created_at":"2026-05-18T00:15:09Z"},{"alias_kind":"arxiv_version","alias_value":"1803.07743v4","created_at":"2026-05-18T00:15:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.07743","created_at":"2026-05-18T00:15:09Z"},{"alias_kind":"pith_short_12","alias_value":"IKI2OWAUFXXI","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_16","alias_value":"IKI2OWAUFXXISALB","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_8","alias_value":"IKI2OWAU","created_at":"2026-05-18T12:32:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:IKI2OWAUFXXISALBNTFIQPUISN","target":"record","payload":{"canonical_record":{"source":{"id":"1803.07743","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2018-03-21T04:16:14Z","cross_cats_sorted":[],"title_canon_sha256":"4ce349c6b4e8c3fa02991827d17c51189d7ab1b5f882054993f45b5ac0e20eff","abstract_canon_sha256":"dd80f0fc087ff25bd94965e371dd92b8047de264fe6bb00157b18505db5d886e"},"schema_version":"1.0"},"canonical_sha256":"4291a758142dee8901616cca883e88934ceecb34e469980be48605977a6b88c1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:09.608177Z","signature_b64":"qtq7TGHXiZok8aGiM1xHgnWTvfCVq+DUiVqxk7ty+zLHKlvEYUeOiJJ/GndSUkyvodHD1o2eXxzhh/d9dxuRDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4291a758142dee8901616cca883e88934ceecb34e469980be48605977a6b88c1","last_reissued_at":"2026-05-18T00:15:09.607621Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:09.607621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1803.07743","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:15:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xc6QKn5DFfFp+BDv3V0pMmpaP52GiIp7/BqBbQ9/5AXtf+1lRVOseNds3E0OYiagw0GPTiZBp1NExdMuxIs+Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T14:49:42.532713Z"},"content_sha256":"a4115ef5e2ba11f7ce5ebdd827b3fd3c488fdab2dcd61e50af9847499fb14230","schema_version":"1.0","event_id":"sha256:a4115ef5e2ba11f7ce5ebdd827b3fd3c488fdab2dcd61e50af9847499fb14230"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:IKI2OWAUFXXISALBNTFIQPUISN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Supplementary Condition for the Convergence of the Control Policy during Adaptive Dynamic Programming","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Nitin Sharma, Xuefeng Bao, Zhi-Hong Mao","submitted_at":"2018-03-21T04:16:14Z","abstract_excerpt":"Reinforcement learning based adaptive/approximate dynamic programming (ADP) is a powerful technique to determine an approximate optimal controller for a dynamical system. These methods bypass the need to analytically solve the nonlinear Hamilton-Jacobi-Bellman equation, whose solution is often to difficult to determine but is needed to determine the optimal control policy. ADP methods usually employ a policy iteration algorithm that evaluates and improves a value function at every step to find the optimal control policy. Previous works in ADP have been lacking a stronger condition that ensures"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.07743","kind":"arxiv","version":4},"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":"2026-05-18T00:15:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IZdpgEHoQshsioLWF2pArAOL6rqB9MWv08M1jNX745agA/EduGlJ4ir1UiKtK8nLQYNy85y5BDyjA4x+GoqCAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T14:49:42.533060Z"},"content_sha256":"9c5bd296e78cd275d662ffddfc7eb149e64dddcb641ba7c8ecaa8e2e43a96a8c","schema_version":"1.0","event_id":"sha256:9c5bd296e78cd275d662ffddfc7eb149e64dddcb641ba7c8ecaa8e2e43a96a8c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IKI2OWAUFXXISALBNTFIQPUISN/bundle.json","state_url":"https://pith.science/pith/IKI2OWAUFXXISALBNTFIQPUISN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IKI2OWAUFXXISALBNTFIQPUISN/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":"2026-06-26T14:49:42Z","links":{"resolver":"https://pith.science/pith/IKI2OWAUFXXISALBNTFIQPUISN","bundle":"https://pith.science/pith/IKI2OWAUFXXISALBNTFIQPUISN/bundle.json","state":"https://pith.science/pith/IKI2OWAUFXXISALBNTFIQPUISN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IKI2OWAUFXXISALBNTFIQPUISN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:IKI2OWAUFXXISALBNTFIQPUISN","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":"dd80f0fc087ff25bd94965e371dd92b8047de264fe6bb00157b18505db5d886e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2018-03-21T04:16:14Z","title_canon_sha256":"4ce349c6b4e8c3fa02991827d17c51189d7ab1b5f882054993f45b5ac0e20eff"},"schema_version":"1.0","source":{"id":"1803.07743","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.07743","created_at":"2026-05-18T00:15:09Z"},{"alias_kind":"arxiv_version","alias_value":"1803.07743v4","created_at":"2026-05-18T00:15:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.07743","created_at":"2026-05-18T00:15:09Z"},{"alias_kind":"pith_short_12","alias_value":"IKI2OWAUFXXI","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_16","alias_value":"IKI2OWAUFXXISALB","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_8","alias_value":"IKI2OWAU","created_at":"2026-05-18T12:32:31Z"}],"graph_snapshots":[{"event_id":"sha256:9c5bd296e78cd275d662ffddfc7eb149e64dddcb641ba7c8ecaa8e2e43a96a8c","target":"graph","created_at":"2026-05-18T00:15:09Z","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":"Reinforcement learning based adaptive/approximate dynamic programming (ADP) is a powerful technique to determine an approximate optimal controller for a dynamical system. These methods bypass the need to analytically solve the nonlinear Hamilton-Jacobi-Bellman equation, whose solution is often to difficult to determine but is needed to determine the optimal control policy. ADP methods usually employ a policy iteration algorithm that evaluates and improves a value function at every step to find the optimal control policy. Previous works in ADP have been lacking a stronger condition that ensures","authors_text":"Nitin Sharma, Xuefeng Bao, Zhi-Hong Mao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2018-03-21T04:16:14Z","title":"A Supplementary Condition for the Convergence of the Control Policy during Adaptive Dynamic Programming"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.07743","kind":"arxiv","version":4},"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:a4115ef5e2ba11f7ce5ebdd827b3fd3c488fdab2dcd61e50af9847499fb14230","target":"record","created_at":"2026-05-18T00:15:09Z","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":"dd80f0fc087ff25bd94965e371dd92b8047de264fe6bb00157b18505db5d886e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2018-03-21T04:16:14Z","title_canon_sha256":"4ce349c6b4e8c3fa02991827d17c51189d7ab1b5f882054993f45b5ac0e20eff"},"schema_version":"1.0","source":{"id":"1803.07743","kind":"arxiv","version":4}},"canonical_sha256":"4291a758142dee8901616cca883e88934ceecb34e469980be48605977a6b88c1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4291a758142dee8901616cca883e88934ceecb34e469980be48605977a6b88c1","first_computed_at":"2026-05-18T00:15:09.607621Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:15:09.607621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qtq7TGHXiZok8aGiM1xHgnWTvfCVq+DUiVqxk7ty+zLHKlvEYUeOiJJ/GndSUkyvodHD1o2eXxzhh/d9dxuRDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:15:09.608177Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.07743","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a4115ef5e2ba11f7ce5ebdd827b3fd3c488fdab2dcd61e50af9847499fb14230","sha256:9c5bd296e78cd275d662ffddfc7eb149e64dddcb641ba7c8ecaa8e2e43a96a8c"],"state_sha256":"d727183c4697e34f24b9e3cfa74347e1e987a0ed3a9fd06f0ce4f987faa3b590"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W98WCF5f7cPcHFiFvxQaBu1kapRBfM3eJNbKuHvf3LU53F8z2ac8/T9SLJPvDimY8idvQjijrwyvuhaOqXpCBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-26T14:49:42.535056Z","bundle_sha256":"faeb3d186d543dfb7c11069bc797024501cddd33c5dc4d8da80a195cffeb0142"}}