Fuzzy Sarsa: An approach to linear function approximation in reinforcement learning

نویسنده

  • L. Tokarchuk
چکیده

This paper investigates two different approaches to learning using an agent electronic marketplace as test bed. The types of learning considered in this paper include the temporal difference (TD) learning algorithm Sarsa, and two new fuzzified versions of this algorithm, FQ Sarsa and Fuzzy Sarsa. We implement the three learning algorithms in an agent test bed in order to determine their usefulness in the context of an electronic marketplace. We present the results of various tests demonstrating that the Fuzzy Sarsa algorithm, while having the smallest state space, is also the more effective method of learning.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Fuzzy and Tile Coding Function Approximation in Agent Coevolution

Reinforcement learning (RL) is a machine learning technique for sequential decision making. This approach is well proven in many small-scale domains. The true potential of this technique cannot be fully realised until it can adequately deal with the large domain sizes that typically describe real world problems. RL with function approximation is one method of dealing with the domain size proble...

متن کامل

ارائه الگوریتم جدید Fuzzy SARSA بهمنظور پیش بینی نوسانات سطح قند خون بیماران مبتلا به دیابت نوع یک

Background: One of the serious complications of type 1 diabetes is a sudden increase and drop in blood glucose levels causing risks of anesthesia and coma. Thus, an important step towards the optimal control of the disease is to use intelligent methods with low error rate and available information in order to predict and prevent such complications. In this paper, a combined Fuzzy SARSA algorith...

متن کامل

The Fuzzy Sars’a’(λ) Learning Approach Applied to a Strategic Route Learning Robot Behaviour

This paper presents a novel Fuzzy Sarsa(λ) Learning (FSλL) approach applied to a strategic route leaning task of a mobile robot. FSλL is a hybrid architecture that combines Reinforcement Learning and Fuzzy Logic control. The Sarsa(λ) Learning algorithm is used to tune the rule-base of a Fuzzy Logic controller which has been tested in a route learning task. The robot explores its environment usi...

متن کامل

Exploration and exploitation balance management in fuzzy reinforcement learning

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 ...

متن کامل

Online Transfer Learning in Reinforcement Learning Domains

This paper proposes an online transfer framework to capture the interaction among agents and shows that current transfer learning in reinforcement learning is a special case of online transfer. Furthermore, this paper re-characterizes existing agents-teaching-agents methods as online transfer and analyze one such teaching method in three ways. First, the convergence of Qlearning and Sarsa with ...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2005