Here we introduce a simple actor-critic model of eye movements during category learning that we call RLAttn (Reinforcement Learning of Attention). RLAttn stores the rewards it receives for making decisions or performing actions, while attempting to associate stimuli with particular categories. Over multiple trials, RLAttn learns that a large reward is most likely when the values of the relevant...

In this research, a novel computational intelligencebased algorithm to detect artifacts, specifically arrows, in medical images is presented. Image analyses techniques are developed to find the symbols and text automatically. Features are computed from the shape of arrow for the discrimination of arrows from other artifacts. We investigate a biologically-inspired reinforcement learning (RL) app...

Instrumental conditioning studies how animals and humans choose actions appropriate to the affective structure of an environment. According to recent reinforcement learning models, two distinct components are involved: a "critic," which learns to predict future reward, and an "actor," which maintains information about the rewarding outcomes of actions to enable better ones to be chosen more fre...

This paper presents the first actor-critic algorithm for o↵-policy reinforcement learning. Our algorithm is online and incremental, and its per-time-step complexity scales linearly with the number of learned weights. Previous work on actor-critic algorithms is limited to the on-policy setting and does not take advantage of the recent advances in o↵policy gradient temporal-di↵erence learning. O↵...