Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Mete, Akshay"'
We consider the infinite-horizon linear Markov Decision Processes (MDPs), where the transition probabilities of the dynamic model can be linearly parameterized with the help of a predefined low-dimensional feature mapping. While the existing regressi
Externí odkaz:
http://arxiv.org/abs/2310.11515
Minimum variance controllers have been employed in a wide-range of industrial applications. A key challenge experienced by many adaptive controllers is their poor empirical performance in the initial stages of learning. In this paper, we address the
Externí odkaz:
http://arxiv.org/abs/2305.16974
We consider the problem of controlling an unknown stochastic linear system with quadratic costs - called the adaptive LQ control problem. We re-examine an approach called ''Reward Biased Maximum Likelihood Estimate'' (RBMLE) that was proposed more th
Externí odkaz:
http://arxiv.org/abs/2201.10542
The Reward-Biased Maximum Likelihood Estimate (RBMLE) for adaptive control of Markov chains was proposed to overcome the central obstacle of what is variously called the fundamental "closed-identifiability problem" of adaptive control, the "dual cont
Externí odkaz:
http://arxiv.org/abs/2011.07738
Partial sharing allows providers to possibly pool a fraction of their resources when full pooling is not beneficial to them. Recent work in systems without sharing has shown that redundancy can improve performance considerably. In this paper, we comb
Externí odkaz:
http://arxiv.org/abs/1906.03587