An algorithm for reduct cardinality minimization

AbouEisha, Hassan; Farhan, Mohammed Al; Chikalov, Igor; Moshkov, Mikhail

doi:10.1109/grc.2013.6740370

Cited by 2 publications

(1 citation statement)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The cardinality is represented by the number of elements which are not 0 in the matrix, such as the cardinality of y is 1, when the vector is y = [y 1 , y 2 , y 3 , y 4 ] = [0, 0, 0, 2]. Solving the minimization problem for a cardinality mechanism can be regarded as a series of optimization issues [36]. These problems talked before are usually deployed in graph-related problems with randomized approaches, as random separation [37], [38], which considers the solutions with exactly a fixed number k of elements that optimizes the solution values.…”

Section: Cardinality Minimization Techniquementioning

confidence: 99%

An Approximate Quadratic Programming for Efficient Bellman Equation Solution

Cheng

Guo

et al. 2019

IEEE Access

View full text Add to dashboard Cite

This paper proposes an efficient algorithm which relies on quadratic programming for approximately solving the Bellman equation in reinforcement learning problem and guarantees to return optimal decision parameters. Through further applying universal approximation and fixed cardinality minimization techniques, the proposed algorithm in one hand expands the representation ability of basic linear value functions, on the other hand, it guarantees the convergence of the Bellman error. Experimental results on two canonical reinforcement learning scenarios demonstrate that the proposed algorithm achieves similar or better performance than the state-of-the-art algorithms, while reduces the computation time significantly and improves the robustness of the algorithm against state uncertainty. INDEX TERMS Markov decision processes, approximate quadratic programming, Bellman equation solutions, universal approximation, fixed cardinality.

show abstract

Section: Cardinality Minimization Techniquementioning

confidence: 99%