Abstract. This article presents an algorithm that combines a FAST-based algorithm (Flexible Adaptable-Size Topology), called ARM, and Q-learning algorithm. The ARM is a self organizing architecture. Dynamically adjusting the size of sensitivity regions of each neuron and adaptively pruning one of the redundant neurons, the ARM can preserve resources (available neurons) to accommodate more categories. The Q-learning is a dynamic programming-based reinforcement learning method, in which the learned action-value function, Q, directly approximates Q*, the optimal action-value function, independent of the policy being followed. In the proposed method, the ARM acts as a cluster to categorize input vectors from the outside world. Clustered results...
In the past decade, research in neurocomputing has been divided into two relatively welldefined trac...
Platt's resource-allocation network (RAN) (Platt, 1991a, 1991b) is modified for a reinforcement...
The purpose of this paper is to propose a Neural-Q_learning approach designed for online learning of...
Reinforcement learning is a technique to learn suitable action policies that maximize utility, via t...
Q-learning can be used to find an optimal action-selection policy for any given finite Markov Decisi...
The paper explores a very simple agent design method called Q-decomposition, wherein a com-plex agen...
Q-Learning is a method for solving reinforcement learning problems. Reinforcement learning problems ...
This paper presents a novel incremental algorithm that combines Q-learning, a well-known dynamic-pro...
The paper analyzes one of the main reinforcement learning methods - Q-learning, which is actively us...
We present a variant of the Q-learning algorithm with automatic control of the exploration rate by a...
Abstract. Q-learning can be used to learn a control policy that max-imises a scalar reward through i...
Q-learning has often been used to learn primitive behaviors, or to coordinate a limited set of motor...
Scaling down robots to miniature size introduces many new challenges including memory and program si...
This paper proposes a neural network based reinforcement learning controller that is able to learn c...
This paper presents a learning system that uses Q-learning with a resource allocating network (RAN) ...
In the past decade, research in neurocomputing has been divided into two relatively welldefined trac...
Platt's resource-allocation network (RAN) (Platt, 1991a, 1991b) is modified for a reinforcement...
The purpose of this paper is to propose a Neural-Q_learning approach designed for online learning of...
Reinforcement learning is a technique to learn suitable action policies that maximize utility, via t...
Q-learning can be used to find an optimal action-selection policy for any given finite Markov Decisi...
The paper explores a very simple agent design method called Q-decomposition, wherein a com-plex agen...
Q-Learning is a method for solving reinforcement learning problems. Reinforcement learning problems ...
This paper presents a novel incremental algorithm that combines Q-learning, a well-known dynamic-pro...
The paper analyzes one of the main reinforcement learning methods - Q-learning, which is actively us...
We present a variant of the Q-learning algorithm with automatic control of the exploration rate by a...
Abstract. Q-learning can be used to learn a control policy that max-imises a scalar reward through i...
Q-learning has often been used to learn primitive behaviors, or to coordinate a limited set of motor...
Scaling down robots to miniature size introduces many new challenges including memory and program si...
This paper proposes a neural network based reinforcement learning controller that is able to learn c...
This paper presents a learning system that uses Q-learning with a resource allocating network (RAN) ...
In the past decade, research in neurocomputing has been divided into two relatively welldefined trac...
Platt's resource-allocation network (RAN) (Platt, 1991a, 1991b) is modified for a reinforcement...
The purpose of this paper is to propose a Neural-Q_learning approach designed for online learning of...