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...

A new algorithm for reinforcement learning, advantage updating, is described. Advantage updating is a direct learning technique; it does not require a model to be given or learned. It is incremental, requiring only a constant amount of calculation per time step, independent of the number of possible actions, possible outcomes from a given action, or number of states. Analysis and simulation ind...

Research on human and animal behavior has long emphasized its hierarchical structure-the divisibility of ongoing behavior into discrete tasks, which are comprised of subtask sequences, which in turn are built of simple actions. The hierarchical structure of behavior has also been of enduring interest within neuroscience, where it has been widely considered to reflect prefrontal cortical functio...

In this paper, we describe FACS, a new Michigan style architecture able to build Finite-State Automata controllers for agents learning to solve nonMarkov problems. FACS relies on a population of partial automata and implements a Reinforcement Learning algorithm to compute the strength of each automaton and a Genetic Algorithm to select and discover efficient automata. We detail our approach and...

The reinforcement learning scheme proposed in Halici (J. Biosystems 40 (1997) 83) for the random neural network (RNN) (Neural Computation 1 (1989) 502) is based on reward and performs well for stationary environments. However, when the environment is not stationary it suffers from getting stuck to the previously learned action and extinction is not possible. To overcome the problem, the reinfor...

Q-learning in the Reinforcement Learning (RL) field is the powerful and attractive tool to make robots generate autonomous behavior. But it needs large amount of computational cost because of its discrete state and action. To generated smooth trajectory with less computational cost, we propose two ingredients for Qlearning. We applied Q-learning to the simulated two wheeled robot to generate tr...

In this paper we evaluate two Temporal Difference Reinforcement Learning methods on several different tasks to see how well these methods generalize. The tasks were modeled as Markov Decision Processes with a continuous observation space and a discrete action space. Function approximation was done using linear gradient descent with RBFs as features. The tasks were taken from the Polyathlon doma...

Cellular learning automata (CLA) is a distributed computational model which was introduced in the last decade. This model combines the computational power of the cellular automata with the learning power of the learning automata. Cellular learning automata is composed from a lattice of cells working together to accomplish their computational task; in which each cell is equipped with some learni...