This work represents the first step towards a task library system in the reinforcement learning domain. Task libraries could be useful in speeding up the learning of new tasks through task transfer. Related transfer can increase learning rate and can help prevent convergence to sub-optimal policies in reinforcement learning. Unrelated transfer can be extremely detrimental to the learning rate. ...

Psychologists often explore the impact of one act on a subsequent related act. With an eye to the marketing literature, this paper explores two properties of sequential choices that involve the resolution of competing goals. Reinforcement occurs when the goals driving the first choice are made stronger by that choice and result in a congruent subsequent choice. Balance occurs when the first cho...

We present a framework for transfer in reinforcement learning based on the idea that related tasks share some common features, and that transfer can be achieved via those shared features. The framework attempts to capture the notion of tasks that are related but distinct, and provides some insight into when transfer can be usefully applied to a problem sequence and when it cannot. We apply the ...

ii Abstract (in Swedish) iiiin Swedish) iii

We introduce the mathematical model for time variable reinforcement learning. The policy, the rewards or reinforcement function and the transition probabilities may depend on the progress of the time t. We prove that under certain conditions slightly changed methods of classical dynamic programming assure finding the optimal policy. For that we deduct the Bellman equation for the time variable ...

TAO JIANG, Ph.D. THESIS, COMMUNICATIONS RESEARCH GROUP, UNIVERSITY OF YORK 2011 Abstract This thesis investigates how distributed reinforcement learning-based resource assignment algorithms can be used to improve the performance of a cognitive radio system. Decision making in most wireless systems today, including most cognitive radio systems in development, depends purely on instantaneous meas...

We present Network Reinforcement Learning (NRL) as more efficient and robust than traditional reinforcement learning in complex environments. Combined with Configural Memory (Pearce, 1994), NRL can generalize from its experiences to novel stimuli, and learn how to deal with anomalies as well. We show how configural memory with NRL accounts for human and monkey data on a classic categorization p...

A new online clustering method based on not only reinforcement and competitive learning but also pursuit algorithm (Pursuit Reinforcement Competitive Learning: PRCL) as well as learning automata is proposed for reaching a relatively stable clustering solution in comparatively short time duration. UCI repository data which are widely used for evaluation of clustering performance in usual is used...

I examine a dynamic model of network formation in which individuals use reinforcement learning to choose their actions. Typically, economic models of network formation assume the entire network structure to be known to all individuals involved. The introduction of reinforcement learning allows us to relax this assumption. Q-learning is a reinforcement learning algorithm from the artificial inte...