Latent Learning in Agents

  title={Latent Learning in Agents},
  author={Rati Sharma},
Various cognitive models have been proposed to determine optimal paths in spatial navigation tasks, some of which demonstrate latent learning in Agents. We view and present the model as a Reinforcement Learning problem by using QLearning and Model-Based Learning in a deterministic environment. This paper uses a QLearning algorithm and compares its performance with the Dyna (Model based) algorithm on Blocking and Shortcut problems. We conclude that using Model-Based Reinforcement learning… CONTINUE READING