Q-Learning with Hidden-Unit Restarting

نویسنده

  • Charles W. Anderson
چکیده

Platt's resource-allocation network (RAN) (Platt, 1991a, 1991b) is modified for a reinforcement-learning paradigm and to "restart" existing hidden units rather than adding new units. After restarting, units continue to learn via back-propagation. The resulting restart algorithm is tested in a Q-Iearning network that learns to solve an inverted pendulum problem. Solutions are found faster on average with the restart algorithm than without it.

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

A Study of Adaptive Restarting Strategies for Solving Constraint Satisfaction Problems

In this paper we present a study of four generic strategies for solving constraint satisfaction problems (CSPs) of any kind, be they soluble or insoluble. All four methods combine learning with restarting, two use a fixed cutoff restarting strategy followed by a run to completion, the other two use universal restarting strategies where the cutoff varies from run to run. Learning takes the form ...

متن کامل

Deep reinforcement learning for time series: playing idealized trading games

Deep Q-learning is investigated as an end-to-end solution to estimate the optimal strategies for acting on time series input. Experiments are conducted on two idealized trading games. 1) Univariate: the only input is a wave-like price time series, and 2) Bivariate: the input includes a random stepwise price time series and a noisy signal time series, which is positively correlated with future p...

متن کامل

بررسی تجارب دانشجویان از برنامه درسی مستتر در دانشکده پرستاری و مامایی دانشگاه علوم پزشکی اصفهان

  Background : The hidden curriculum has great impact on students' learning. The present study was conducted on Nursing and Midwifery students to determine their experience with the hidden curriculum. Materials and methods : It was a combined survey achieved in two stages on Nursing and Midwifery students. During the first stage, a free interview was carried out to determine their attitudes tow...

متن کامل

Learning Restarting Automata by Genetic Algorithms

Restarting automaton is a special type of a linear bounded automaton designed for modelling the so-called analysis by reduction. We use genetic algorithms to learn restarting automata to recognize languages according to input consisting of sets of positive and negative examples of words from the language together with positive and negative examples of simplifications.

متن کامل

Pulling back error to the hidden-node parameter technology: Single-hidden-layer feedforward network without output weight

According to conventional neural network theories, the feature of single-hidden-layer feedforward neural networks(SLFNs) resorts to parameters of the weighted connections and hidden nodes. SLFNs are universal approximators when at least the parameters of the networks including hidden-node parameter and output weight are exist. Unlike above neural network theories, this paper indicates that in o...

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 1992