Hamiltonian Monte Carlo based Path Integral for Stochastic Optimal Control

Akshay, P.; Vrushabh, D.; Sonam, K.; Wagh, Sushama; Singh, Navdeep

doi:10.1109/med48518.2020.9183150

Cited by 2 publications

(2 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The technique developed in this article is not restrictive to PBCNs and can be diversified to sequential decision‐making problems under uncertainty. Furthermore, for variance improvements, efficient sampling techniques such as Hamiltonian Monte Carlo sampling 62 and importance sampling 47 can be employed to deal with higher‐dimensional distributions.…”

Section: Conclusion and Future Scopementioning

confidence: 99%

Optimal control of probabilistic Boolean control networks: A scalable infinite horizon approach

Kharade¹,

Sutavani

Wagh³

et al. 2021

Intl J Robust & Nonlinear

View full text Add to dashboard Cite

One of the major issues in systems biology is developing control theory for gene regulatory networks (GRNs). Particularly, an important objective is to develop therapeutic intervention strategies to alter regulatory dynamics of GRNs to avoid undesired or diseased states. Several optimal control strategies have been developed to find therapeutic intervention strategies for small (or medium) sized GRNs modeled as probabilistic Boolean control networks (PBCNs). However, due to the humongous nature of GRNs, we require an optimal control strategy that scales to large systems without posing any constraints on the network dynamics. In this article, we formulate the infinite horizon discounted cost optimal control problem by leveraging the Markov decision process (MDP) based PBCN structure to model GRNs. Further, we design a stationary optimal control strategy, thereby avoiding the states associated with a disease. An augmented state space is defined to facilitate the control design method. By exploiting Kullback-Leibler (KL) divergence and the log transformation of the cost function referred to as the desirability function, the optimal control is devised using the path integral (PI) approach. We propose a sampling-based technique for the approximation of the PI and hence the optimal control of PBCNs. The sampling-based strategy is amicable to parallel implementation, thereby addressing the optimal control problem of large-scale PBCNs. Finally, the viability of the results in the article is shown by some illustrative examples.

show abstract

Section: Conclusion and Future Scopementioning

confidence: 99%

Optimal control of probabilistic Boolean control networks: A scalable infinite horizon approach

Kharade¹,

Sutavani

Wagh³

et al. 2021

Intl J Robust & Nonlinear

View full text Add to dashboard Cite

show abstract

“…Similarly, the acrobot system is a double pendulum, but the actuated joint is the elbow, and the free joint is the shoulder [25]. Another underactuated mechanical system is the cartpendulum, studied in [26][27]. The cart-pendulum consists of a passive pendulum mounted on a cart.…”

Section: Introductionmentioning

confidence: 99%

Combined adaptive neural network and regressor‐based trajectory tracking control of flexible joint robots

Montoya–Cháirez¹,

Moreno–Valenzuela²,

Santibáñez

et al. 2021

IET Control Theory & Appl

View full text Add to dashboard Cite

By relying on the input-output feedback linearization approach, a novel adaptive controller for flexible joint robots is proposed in this work. First, a model-based controller is developed to get a structure that is useful in the development of the adaptive controller. The adaptive version is developed by using two techniques. To stabilize the output function, an adaptive neural network controller is used, which approximates the non-linear function that contains the uncertainties. The desired rotor position required by the input-output feedback linearization controller is defined with the structure of a link dynamics adaptive regressor-based controller. The main reason to adopt the mentioned structure in the definition of the desired rotor link position is to guarantee its differentiability. Real-time experiment comparisons among the model-based controller, a model-based controller with desired compensation, an adaptive controller based on joint torque feedback, and an adaptive neural network-based controller are carried out. Experimental results support the theory reported in this document and the accuracy of the proposed approach.

show abstract

Hamiltonian Monte Carlo based Path Integral for Stochastic Optimal Control

Cited by 2 publications

References 10 publications

Optimal control of probabilistic Boolean control networks: A scalable infinite horizon approach

Optimal control of probabilistic Boolean control networks: A scalable infinite horizon approach

Combined adaptive neural network and regressor‐based trajectory tracking control of flexible joint robots

Contact Info

Product

Resources

About