{"cited_by_count":272210,"description":"This cluster of papers focuses on the application of Adaptive Dynamic Programming and Reinforcement Learning techniques to solve optimal control problems in continuous-time nonlinear systems. It explores the use of neural networks, policy iteration, actor-critic algorithms, and $H_{infty}$ control for online learning and feedback control in various domains such as robotics, energy management, and multi-agent systems.","display_name":"Adaptive Dynamic Programming Control","domain_id":"3","external_ids":{"openalex":"https://openalex.org/T12794","wikipedia":"https://en.wikipedia.org/wiki/Adaptive_dynamic_programming"},"field_id":"17","id":"T12794","keywords":[{"display_name":"adaptive dynamic programming","id":"adaptive-dynamic-programming","score":0.6572,"url":"https://openalex.org/keywords/adaptive-dynamic-programming"},{"display_name":"policy iteration","id":"policy-iteration","score":0.4379,"url":"https://openalex.org/keywords/policy-iteration"},{"display_name":"approximate dynamic programming","id":"approximate-dynamic-programming","score":0.2585,"url":"https://openalex.org/keywords/approximate-dynamic-programming"},{"display_name":"value iteration","id":"value-iteration","score":0.2545,"url":"https://openalex.org/keywords/value-iteration"},{"display_name":"unknown dynamics","id":"unknown-dynamics","score":0.2123,"url":"https://openalex.org/keywords/unknown-dynamics"},{"display_name":"critic neural network","id":"critic-neural-network","score":0.8249,"url":"https://openalex.org/keywords/critic-neural-network"},{"display_name":"optimal tracking control","id":"optimal-tracking-control","score":0.4838,"url":"https://openalex.org/keywords/optimal-tracking-control"},{"display_name":"integral reinforcement learning","id":"integral-reinforcement-learning","score":0.7382,"url":"https://openalex.org/keywords/integral-reinforcement-learning"},{"display_name":"continuous-time nonlinear systems","id":"nonlinear-continuous-time-systems","score":0.2165,"url":"https://openalex.org/keywords/nonlinear-continuous-time-systems"},{"display_name":"adaptive optimal control","id":"adaptive-optimal-control","score":0.3623,"url":"https://openalex.org/keywords/adaptive-optimal-control"},{"display_name":"Hamilton-Jacobi-Isaacs equation","id":"hamilton-jacobi-isaacs-equation","score":0.3494,"url":"https://openalex.org/keywords/hamilton-jacobi-isaacs-equation"},{"display_name":"actor-critic neural networks","id":"actor-critic-neural-networks","score":0.4997,"url":"https://openalex.org/keywords/actor-critic-neural-networks"},{"display_name":"adaptive critic","id":"adaptive-critic","score":0.6155,"url":"https://openalex.org/keywords/adaptive-critic"},{"display_name":"critic network","id":"critic-network","score":0.5734,"url":"https://openalex.org/keywords/critic-network"},{"display_name":"optimality equation","id":"optimality-equation","score":0.4306,"url":"https://openalex.org/keywords/optimality-equation"},{"display_name":"stationary optimal policy","id":"optimal-stationary-policy","score":0.3696,"url":"https://openalex.org/keywords/optimal-stationary-policy"},{"display_name":"heuristic dynamic programming","id":"heuristic-dynamic-programming","score":0.5374,"url":"https://openalex.org/keywords/heuristic-dynamic-programming"},{"display_name":"stationary policies","id":"stationary-policies","score":0.314,"url":"https://openalex.org/keywords/stationary-policies"},{"display_name":"existence of optimal policies","id":"existence-of-optimal-policies","score":0.3693,"url":"https://openalex.org/keywords/existence-of-optimal-policies"},{"display_name":"continuous-time Markov decision processes","id":"continuous-time-markov-decision-processes","score":0.2275,"url":"https://openalex.org/keywords/continuous-time-markov-decision-processes"},{"display_name":"average cost criterion","id":"average-cost-criterion","score":0.3091,"url":"https://openalex.org/keywords/average-cost-criterion"},{"display_name":"action network","id":"action-network","score":0.2535,"url":"https://openalex.org/keywords/action-network"},{"display_name":"controlled Markov chains","id":"controlled-markov-chains","score":0.2575,"url":"https://openalex.org/keywords/controlled-markov-chains"},{"display_name":"unbounded costs","id":"unbounded-costs","score":0.5015,"url":"https://openalex.org/keywords/unbounded-costs"},{"display_name":"neural network identifier","id":"neural-network-identifier","score":0.3532,"url":"https://openalex.org/keywords/neural-network-identifier"}],"legacy_keywords":["Adaptive Dynamic Programming","Reinforcement Learning","Optimal Control","Neural Networks","Continuous-Time Systems","Nonlinear Systems","Policy Iteration","Actor-Critic Algorithm","$H_{infty}$ Control","Online Learning"],"openalex_id":"https://openalex.org/T12794","source_created_date":"2024-01-23T15:27:15","source_updated_date":"2026-10-17T03:02:00","subfield_id":"1703","url":"/topics/T12794","works_api_url":"https://api.openalex.org/works?filter=topics.id:T12794","works_count":13276,"label":"Adaptive Dynamic Programming Control","provider":"openalex","revision":"6e225572734960d6","taxonomy_revision":"f050b5d4780b1289","title":"Adaptive Dynamic Programming Control","kind":"topic-directory","aeo_cohort":"topic-directory","catalogue_revision":"f050b5d4780b1289","numeric_address":"38285307485521111","address_version":"morton4x16-v1","coordinates":[3,17,1703,12794],"answer_status":"Directory metadata; local answer requires separate source review","truth_status":"Subject descriptor, not a factual answer or a demonstrated knowledge gap","reviewed_answer":null}