Recently reinforcement learning has received much attention as a learning method (Sutton, 1988; Watkins & Dayan, 1992). It does not need a priori knowledge and has higher capability of reactive and adaptive behaviors. However there are some significant problems in applying it to real problems. Some of them are deep cost of learning and large size of actionstate space. The Q-learning (Watkins & ...

Action effects do not occur randomly in time but follow our actions at specific delays. The ideomotor principle (IMP) is widely used to explain how the relation between actions and contingently following effects is acquired and numerous studies demonstrate robust action-effect learning. Yet, little is known about the acquisition of temporal delays of action effects. Here, we demonstrate that pa...

Virtual worlds, computer-based simulated environments in which users interact via avatars, provide an opportunity for the highly realistic enactment of real life activities online. Unlike computer games, which have a pre-defined purpose, pay-off structure, and action patterns, virtual worlds can leave many of these elements for users to determine. One such world, Second Life (SL), is frequently...

This paper proposes statistic learning based Q-learning algorithm for Multi-Agent System, the agent can learn other agents’ action policies through observing and counting the joint action, a concise but useful hypothesis is adopted to denote the optimal policies of other agents, the full joint probability of policies distribution guarantees the optimal action choice to the learning agent. The a...