Averaged Reward Reinforcement Learning Applied to Fuzzy Rule Tuning
نویسندگان
چکیده
Fuzzy rules for control can be eeectively tuned via reinforcement learning. Reinforcement learning is a weak learning method, which only requires information on the success or failure of the control application. The tuning process allows people to generate fuzzy rules which are unable to accurately perform control and have them tuned to be rules which provide smooth control. This paper explores a new sim-pliied method of using reinforcement learning for the tuning of fuzzy control rules. It is shown that the learned fuzzy rules provide smoother control in the pole balancing domain than another approach.
منابع مشابه
Learning Classifier Systems Approach for Automated Discovery of Crisp and Fuzzy Hierarchical Production Rules
This research presents a system for post processing of data that takes mined flat rules as input and discovers crisp as well as fuzzy hierarchical structures using Learning Classifier System approach. Learning Classifier System (LCS) is basically a machine learning technique that combines evolutionary computing, reinforcement learning, supervised or unsupervised learning and heuristics to produ...
متن کاملDesign Issues of a Reinforcement-based Self-Learning Fuzzy Controller for Petrochemical Process Control
Fuzzy logic controllers have some often-cited advantages over conventional techniques such as PID control, including easier implementation, accommodation to natural language, and the ability to cover a wider range of operating conditions. One major obstacle that hinders the broader application of fuzzy logic controllers is the lack of a systematic way to develop and modify their rules; as a res...
متن کاملReinforcement structure/parameter learning for neural-network-based fuzzy logic control systems
AbstructThis paper proposes a reinforcement neuralnetwork-based fuzzy logic control system (RNN-FLCS) for solving various reinforcement learning problems. The proposed RNN-FLCS is constructed by integrating two neural-networkbased fuzzy logic controllers (NN-FLC’s), each of which is a connectionist model with a feedforward multilayered network developed for the realization of a fuzzy logic cont...
متن کاملA Fuzzy Reinforcement Learning for a Ball Interception Problem
In this paper, we propose a reinforcement learning method called a fuzzy Q-learning where an agent determines its action based on the inference result by a fuzzy rule-based system. We apply the proposed method to a soccer agent that intercepts a passed ball by another agent. In the proposed method, the state space is represented by internal information the learning agent maintains such as the r...
متن کاملA fuzzy controller with supervised learning assisted reinforcement learning algorithm for obstacle avoidance
Fuzzy logic systems are promising for efficient obstacle avoidance. However, it is difficult to maintain the correctness, consistency, and completeness of a fuzzy rule base constructed and tuned by a human expert. A reinforcement learning method is capable of learning the fuzzy rules automatically. However, it incurs a heavy learning phase and may result in an insufficiently learned rule base d...
متن کامل