Neural Network-Based Solutions for Stochastic Optimal Control Using Path Integrals
Citations
2,446 citations
146 citations
42 citations
37 citations
Cites background from "Neural Network-Based Solutions for ..."
...ming (ADP) [15]–[17]/reinforcement learning (RL) [18], [19] based approximate solutions are sought for optimal control of...
[...]
References
14,965 citations
"Neural Network-Based Solutions for ..." refers methods in this paper
...In this paper, the Metropolis–Hastings sampling scheme [35], [36] is employed to sample trajectories as per the probability distribution given in (21)....
[...]
10,834 citations
"Neural Network-Based Solutions for ..." refers methods in this paper
...Most RL techniques that are employed for solving optimal control problems are based on value iteration [8], policy iteration [8], or Q-learning [10]....
[...]
4,916 citations
"Neural Network-Based Solutions for ..." refers methods in this paper
...Most RL techniques that are employed for solving optimal control problems are based on value iteration [8], policy iteration [8], or Q-learning [10]....
[...]
...Q-learning algorithms are model-free learning algorithms that do not require an explicit system model for solving the optimal control problem....
[...]
4,572 citations
"Neural Network-Based Solutions for ..." refers methods in this paper
...For discrete-time systems, Werbos [5], [6] developed a family of ADP algorithms that effectively uses the actor–critic architecture for solving the optimal control problem....
[...]
4,251 citations