This paper presents a new approach to hierarchical reinforcement learning based on the MAXQ decomposition of the value function. The MAXQ decomposition has both a procedural seman...
— In this paper, we propose two novel indices for type-2 fuzzy rule ranking to identify the most influential fuzzy rules in designing type-2 fuzzy logic systems, and name them a...
Shang-Ming Zhou, Robert John, Francisco Chiclana, ...
We propose two algorithms for Q-learning that use the two-timescale stochastic approximation methodology. The first of these updates Q-values of all feasible state
Dynamic typing is a barrier for JavaScript applications to achieve high performance. Compared with statically typed languages, the major overhead of dynamic typing comes from runt...
We extend a previous type system for the -calculus that guarantees deadlock-freedom. The previous type systems for deadlockfreedom either lacked a reasonable type inference algorit...