The optimistic exploration value function

Gregor, Michal; Spalek, Juraj

doi:10.1109/ines.2015.7329650

Cited by 3 publications

(3 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The following design theorem provides a method to construct an initial linear stabilizing policy u 0 pxq " K 0 x such that the origin is a GES equilibrium state of the closed-loop system (6).…”

Section: A Unconstrained Adpmentioning

confidence: 99%

“…One needs to gather data safely (exploration) in order to best extract information from this data for optimal decision-making (exploitation). One way to solve the exploration and exploitation dilemma is to use optimistic initialization [6]- [9], but this assumes the optimal policy is available until data is obtained that proves otherwise. Such approaches have been applied to robotics applications, where systems with discrete and continuous state-action spaces [10], [11].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Safe Approximate Dynamic Programming via Kernelized Lipschitz Estimation

Chakrabarty

Jha

Buzzard

et al. 2021

IEEE Trans. Neural Netw. Learning Syst.

View full text Add to dashboard Cite

We develop a method for obtaining safe initial policies for reinforcement learning via approximate dynamic programming (ADP) techniques for uncertain systems evolving with discrete-time dynamics. We employ kernelized Lipschitz estimation and semidefinite programming for computing admissible initial control policies with provably high probability. Such admissible controllers enable safe initialization and constraint enforcement while providing exponential stability of the equilibrium of the closed-loop system.

show abstract

Section: A Unconstrained Adpmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Safe Approximate Dynamic Programming via Kernelized Lipschitz Estimation

Chakrabarty

Jha

Buzzard

et al. 2021

IEEE Trans. Neural Netw. Learning Syst.

View full text Add to dashboard Cite

show abstract

“…Decision agent identifies possible faults and performs remedial actions associated with preventive repairs and reconfiguration of manufacturing system. [14] During recording of sensor data are generate events which triggered activation of simulation mechanism. The role of the simulator is to ensure the extraction of experimental values for diagnostic operations on the basis of the data recording from the real environment.…”

Section: Functional Principles Of Maintenance Systemmentioning

confidence: 99%

Maintenance Support System for Reconfigurable Manufacturing Systems

Rakyta¹,

Fusko²,

Haluska³

et al. 2016

DAAAM Proceedings

View full text Add to dashboard Cite

The maintenance process is one of the most important elements within the overall scope of plant and facilities engineering function. It is a broad-based technology area for the industrial, commercial, institutional, and business communities. The broad scope of plant and facilities engineering is continuously changing and growing in importance as a key contributor to the success of a total operation. Elements within it, such as maintenance, energy management and regulatory compliance, have all evolved to new levels of importance for the total operation.

show abstract

RMDDQN-Learning: Computation Offloading Algorithm Based on Dynamic Adaptive Multi -Objective Reinforcement Learning in Internet of Vehicles

Zhang

Wang

et al. 2023

IEEE Trans. Veh. Technol.

View full text Add to dashboard Cite

The optimistic exploration value function

Cited by 3 publications

References 11 publications

Safe Approximate Dynamic Programming via Kernelized Lipschitz Estimation

Safe Approximate Dynamic Programming via Kernelized Lipschitz Estimation

Maintenance Support System for Reconfigurable Manufacturing Systems

RMDDQN-Learning: Computation Offloading Algorithm Based on Dynamic Adaptive Multi -Objective Reinforcement Learning in Internet of Vehicles

Contact Info

Product

Resources

About