The design and coordination of independent specialized skill units (often called action primitives) is fundamental to modern robotics. However, a robot that must act in a complex environment over an extended period of time should do more than just use existing skills: it should learn new skills that increase its capabilities and facilitate later problem solving. Although robots exist that can l...

Animals increase or decrease their future tendency of emitting an action based on whether performing such action has, in the past, resulted in positive or negative reinforcement. An analysis in the companion paper [Zhang, J. (2009). Adaptive learning via selectionism and Bayesianism. Part I: Connection between the two. Neural Networks, 22(3), 220-228] of such selectionist style of learning reve...

Reinforcement learning (RL) is learning from interaction with an environment, from the consequences of action, rather than from explicit teaching. It is the learning performed by an agent by trial and error interactions with a dynamic environment. This paper discusses Reinforcement learning along with application to static routing.

This paper describes a reinforcement learning algorithm for small autonomous mobile robot agents based on sets of fuzzy automata. The task of the robots is to learn how to reactively avoid obstacles. In the approach presented here two or four robots learn simultaneously, with the experiences of each robot being passed onto the other(s). It is shown that an increasing number of robots sharing th...

This paper describes a reinforcement learning algorithm for small mobile robots based on sets of fuzzy automata. The task the robots have to learn is how to reactively avoid obstacles. In mutual learning two robots learn simultaneously, with the experiences of one robot being passed to the second robot. We show that the robot that receives the other robots experiences learns more quickly and ro...

This paper describes a method which senses changing environment by collecting failed instances, uses concept learning for acquiring a precondition for a control policy, and modifies the policy partially in reinforcement learning. The precondition of a policy represents the condition for reaching goals using the policy. Our method learns the precondition of a policy from the instances of policy ...

Many Intelligent Tutoring Systems have been developed using different Artificial Intelligence techniques. In this paper we propose to use Reinforcement Learning for building an intelligent tutoring system to teach autistic students, who can't communicate well with others. In reinforcement learning, a policy is updated for taking appropriate action to teach the student. The main advantage of usi...

REINFORCEMENT LEARNING IN THE JOINT SPACE: VALUE ITERATION IN WORLDS WITH CONTINUOUS STATES AND ACTIONS Christopher Kenneth Monson Department of Computer Science Master of Science Continuous space reinforcement learning algorithms frequently fail to address the possibility of a continuous action space, presumably because of the difficulty of discovering the best action for a particular state. T...

Algorithms for evolutionary computation, which simulate the process of natural selection to solve optimization problems, are an effective tool for discovering high-performing reinforcement-learning policies. Because they can automatically find good representations, handle continuous action spaces, and cope with partial observability, evolutionary reinforcement-learning approaches have a strong ...

Coordination to some equilibrium point is an interesting problem in multi-agent reinforcement learning. In common interest single stage settings this problem has been studied profoundly and efficient solution techniques have been found. Also for particular multi-stage games some experiments show good results. However, for a large scale of problems the agents do not share a common pay-off functi...