A Proposal of Weighted Q-learning for Continuous State and Action Spaces
نویسندگان
چکیده
A kind of weighted Q-Learning algorithm suitable for control systems with continuous state and action spaces was proposed. The hidden layer of RBF network was designed dynamically by virtue of the proposed modified growing neural gas algorithm so as to realize the adaptive understanding of the continuous state space. Based on the standard Q-Learning implemented by RBF network, the weighted Q-Learning was used to solve the control problem with continuous action outputs. Simulation result of mountain car control verified the validity of the proposed weighted Q-Learning algorithm. Copyright © 2005 IFAC
منابع مشابه
A Q-learning Based Continuous Tuning of Fuzzy Wall Tracking
A simple easy to implement algorithm is proposed to address wall tracking task of an autonomous robot. The robot should navigate in unknown environments, find the nearest wall, and track it solely based on locally sensed data. The proposed method benefits from coupling fuzzy logic and Q-learning to meet requirements of autonomous navigations. Fuzzy if-then rules provide a reliable decision maki...
متن کاملOperation Scheduling of MGs Based on Deep Reinforcement Learning Algorithm
: In this paper, the operation scheduling of Microgrids (MGs), including Distributed Energy Resources (DERs) and Energy Storage Systems (ESSs), is proposed using a Deep Reinforcement Learning (DRL) based approach. Due to the dynamic characteristic of the problem, it firstly is formulated as a Markov Decision Process (MDP). Next, Deep Deterministic Policy Gradient (DDPG) algorithm is presented t...
متن کاملSome inequalities involving lower bounds of operators on weighted sequence spaces by a matrix norm
Let A = (an;k)n;k1 and B = (bn;k)n;k1 be two non-negative ma-trices. Denote by Lv;p;q;B(A), the supremum of those L, satisfying the followinginequality:k Ax kv;B(q) L k x kv;B(p);where x 0 and x 2 lp(v;B) and also v = (vn)1n=1 is an increasing, non-negativesequence of real numbers. In this paper, we obtain a Hardy-type formula forLv;p;q;B(H), where H is the Hausdor matrix and 0 < q p 1. Also...
متن کاملEnhanced continuous valued Q-learning for real autonomous robots
Q-learning, a most widely used reinforcement learning method, normally needs well-defined quantized state and action spaces to obtain an optimal policy for accomplishing a given task. This makes it difficult to be applied to real robot tasks because of poor performance of learned behavior due to the failure of quantization of continuous state and action spaces. To deal with this problem, we pro...
متن کاملHierarchical Functional Concepts for Knowledge Transfer among Reinforcement Learning Agents
This article introduces the notions of functional space and concept as a way of knowledge representation and abstraction for Reinforcement Learning agents. These definitions are used as a tool of knowledge transfer among agents. The agents are assumed to be heterogeneous; they have different state spaces but share a same dynamic, reward and action space. In other words, the agents are assumed t...
متن کامل