Learning Automata update their action probabilites on the basis of the response they get from a random environment. They use a reward adaptation rate for a favorable environment's response and a penalty adaptation rate for an unfavorable environment's response. In this correspondence, we introduce Multiple Response learning automata by explicitly classifying the environment responses into a rew...

Improving performance of electrical distribution companies, as the natural monopoly entities in electric industry, has always been one of the main concerns of the regulators. In this paper, a new incentive regulatory scheme is proposed to improve the performances of electrical distribution companies. The proposed scheme utilizes several efficiency assessments and a 3-dimentional reward-penalty ...

Improving performance of electrical distribution companies, as the natural monopoly entities in electric industry, has always been one of the main concerns of the regulators. In this paper, a new incentive regulatory scheme is proposed to improve the performances of electrical distribution companies. The proposed scheme utilizes several efficiency assessments and a 3-dimentional reward-penalty ...

We propose and analyze a self-adjusting Quality of Service (QoS) control scheme with the goal of optimizing the system reward as a result of servicing different priority clients with varying workload, QoS and reward/penalty requirements. Our scheme is based on resource partitioning and designated “degrade QoS areas” such that system resources are partitioned into priority areas each of which is...

The regulatory schemes currently used for reliability improvement have weaknesses in the provision of quality services based on the customers’ perspective. These schemes consider the average of the service as a criterion to incentivize or penalize the distribution system operators (DSOs). On the other hand, most DSOs do not differentiate electricity services at the customer level, due to the st...

This paper analyzes situations in which a project consisting of several activities is not realized according to plan. If the project is expedited, a reward arises. Analogously, a penalty arises if the project is delayed. This paper considers the case of arbitrary nondecreasing reward and penalty functions on the total expedition and delay, respectively. Attention is focused on how to divide the...

Behavior rests on the experience of reinforcement and punishment. It has been unclear whether reinforcement and punishment act as oppositely valenced components of a single behavioral factor, or whether these two kinds of outcomes play fundamentally distinct behavioral roles. To this end, we varied the magnitude of a reward or a penalty experienced following a choice using monetary tokens. The ...

Reinforcement Learning is a kind of machine learning. It aims to adapt an agent to a given environment with a clue to a reward. In general, the purpose of reinforcement learning system is to acquire an optimum policy that can maximize expected reward per an action. However, it is not always important for any environment. Especially, if we apply reinforcement learning system to engineering, we e...

Monkey studies report greater activity in the lateral intraparietal area and more efficient saccades when targets coincide with the location of prior reward cues, even when cue location does not indicate which responses will be rewarded. This suggests that reward can modulate spatial attention and visual selection independent of the "action value" of the motor response. Our goal was first to de...

A learning automaton (LA) is an automaton that interacts with a random environment, having as its goal the task of learning the optimal action based on its acquired experience. Many learning automata (LAs) have been proposed, with the class of estimator algorithms being among the fastest ones, Thathachar and Sastry, through the pursuit algorithm, introduced the concept of learning algorithms th...