Artificial Intelligence - Special issue: artificial intelligence research in Japan
Introduction to Reinforcement Learning
Introduction to Reinforcement Learning
Dynamic balance of a biped robot using fuzzy reinforcement learning agents
Fuzzy Sets and Systems - Special issue: Fuzzy set techniques for intelligent robotic systems
A reinforcement learning adaptive fuzzy controller for robots
Fuzzy Sets and Systems - Theme: Modeling and control
Reinforcement learning based on local state feature learning and policy adjustment
Information Sciences—Informatics and Computer Science: An International Journal - Special issue: Introduction to multimedia and mobile agents
A proposed method for learning rule weights in fuzzy rule-based classification systems
Fuzzy Sets and Systems
Zero-order TSK-type fuzzy system learning using a two-phase swarm intelligence algorithm
Fuzzy Sets and Systems
Dynamic tuning of online data migration policies in hierarchical storage systems using reinforcement learning
Fuzzy inference system learning by reinforcement methods
IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews
Online tuning of fuzzy inference systems using dynamic fuzzy Q-learning
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
A new Q-learning algorithm based on the metropolis criterion
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
IEEE Transactions on Fuzzy Systems
Synthesized design of a fuzzy logic controller for an underactuated unicycle
Fuzzy Sets and Systems
Backward Q-learning: The combination of Sarsa algorithm and Q-learning
Engineering Applications of Artificial Intelligence
Hi-index | 0.20 |
This paper offers a fuzzy balance management scheme between exploration and exploitation, which can be implemented in any critic-only fuzzy reinforcement learning method. The paper, however, focuses on a newly developed continuous reinforcement learning method, called fuzzy Sarsa learning (FSL) due to its advantages. Establishing balance greatly depends on the accuracy of action value function approximation. At first, the overfitting problem in approximating action value function in continuous reinforcement learning algorithms is discussed, and a new adaptive learning rate is proposed to prevent this problem. By relating the learning rate to the inverse of ''fuzzy visit value'' of the current state, the training data set is forced to have uniform effect on the weight parameters of the approximator and hence overfitting is resolved. Then, a fuzzy balancer is introduced to balance exploration vs. exploitation by generating a suitable temperature factor for the Softmax formula. Finally, an enhanced FSL (EFSL) is offered by integrating the proposed adaptive learning rate and the fuzzy balancer into FSL. Simulation results show that EFSL eliminates overfitting, well manages balance, and outperforms FSL in terms of learning speed and action quality.