We address the problem of automatically constructing basis functions for linear approximation of the value function of a Markov Decision Process (MDP). Our work builds on results ...
With the goal to generate more scalable algorithms with higher efficiency and fewer open parameters, reinforcement learning (RL) has recently moved towards combining classical tec...
The development of control system for the dynamic processes characterizing uncertainties needs the creating of the proper knowledge base for the controller. In this paper, to solve...
—Reinforcement learning is the scheme for unsupervised learning in which robots are expected to acquire behavior skills through self-explorations based on reward signals. There a...
Hiroaki Arie, Tetsuya Ogata, Jun Tani, Shigeki Sug...
A control of real processes requires different approach to neural network learning. The presented modification of backpropagation learning algorithm changes a meaning of learning...