A Neuro - Control Design Based on Fuzzy Reinforcement Learning { Private } Report
نویسندگان
چکیده
This paper describes a neuro-control fuzzy critic design procedure based on reinforcement learning. An important component of the proposed intelligent control configuration is the fuzzy credit assignment unit which acts as a critic, and through fuzzy implications provides adjustment mechanisms to the main controller. The main controller is the neuro-control unit consisting of a full interconnected multi-layer feed forward neural network. The neural network adjusts its weights according to the credit assigned to its output by the fuzz credit assignment unit, using back propagation algorithms. The fuzzy credit assignment unit comprises a fuzzy system with the appropriate fuzzification, knowledge base and defuzzification components. When an external reinforcement signal (a failure signal) is received, sequences of control actions are evaluated and modified by the action applier unit. The desirable ones instruct the neuro-control unit to adjust its weights and are simultaneously stored in the memory unit during the training phase. In response to the internal reinforcement signal (set point threshold deviation), the stored information is retrieved by the action applier unit and utilized for readjustment of the neural network during the recall phase. In order to illustrate the effectiveness of the proposed technique, the controller is tested on a cart-pole balancing problem. Results of extensive simulation studies show a very good performance in comparison with other intelligent control methods.
منابع مشابه
Autonomous System Controller for Vehicles Using Neuro-Fuzzy
this paper presents the approach of neuro fuzzy systems to design autonomous vehicle control system. The purposed intelligent controller deliberates obstacles avoidance, unstructured environment adaptation and speed scheduling of autonomous vehicle based on neuro-fuzzy with reinforcement learning mechanism. The purposed system provides the autonomous vehicle navigation and speed control in unst...
متن کاملQ-Value Based Particle Swarm Optimization for Reinforcement Neuro- Fuzzy System Design
This paper proposes a combination of particle swarm optimization (PSO) and Q-value based safe reinforcement learning scheme for neuro-fuzzy systems (NFS). The proposed Q-value based particle swarm optimization (QPSO) fulfills PSO-based NFS with reinforcement learning; that is, it provides PSO-based NFS an alternative to learn optimal control policies under environments where only weak reinforce...
متن کاملA Reinforcement Learning Algorithm with Evolving Fuzzy Neural Networks
The synergy of the two paradigms, neural network and fuzzy inference system, has given rise to rapidly emerging filed, neuro-fuzzy systems. Evolving neuro-fuzzy systems are intended to use online learning to extract knowledge from data and perform a high-level adaptation of the network structure. We explore the potential of evolving neuro-fuzzy systems in reinforcement learning (RL) application...
متن کاملNeuro-fuzzy control based on the NEFCON-model: recent developments
Fuzzy systems are currently being used in a wide field of industrial and scientific applications. Since the design and especially the optimization process of fuzzy systems can be very time consuming, it is convenient to have algorithms which construct and optimize them automatically. One popular approach is to combine fuzzy systems with learning techniques derived from neural networks. Such app...
متن کاملReinforcement learning based feedback control of tumor growth by limiting maximum chemo-drug dose using fuzzy logic
In this paper, a model-free reinforcement learning-based controller is designed to extract a treatment protocol because the design of a model-based controller is complex due to the highly nonlinear dynamics of cancer. The Q-learning algorithm is used to develop an optimal controller for cancer chemotherapy drug dosing. In the Q-learning algorithm, each entry of the Q-table is updated using data...
متن کامل