Fuzzy reinforcement Learning and dynamic programming
Lecture notes in computer sciencePublished 1 January 1994
H.R. Berenji
Citations20
SJR quartileQ2
SJR score0.35
SNIP0.55
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
It is shown that FQ-Learning provides an alternative solution to this problem which is simpler than the Bellman-Zadeh's fuzzy dynamic programming approach and is applied to a multistage decision making problem.
Abstract
In this paper, we develop a new algorithm called Fuzzy Q-Learning (or FQ-Learning) which extends Watkin's Q-Learning method. It can be used for decision processes in which the goals and/or the constraints, but not necessarily the system under control, are fuzzy in nature. An example of a fuzzy constraint is: "the weight of object A must not be substantially heavier than w" where w is a specified weight. Similarly, an example of a fuzzy goal is: "the robot must be in the vicinity of door k". We show that FQ-Learning provides an alternative solution to this problem which is simpler than the Bellman-Zadeh's fuzzy dynamic programming approach. We apply the algorithm to a multistage decision making problem.
Keywords
Computer Science
ScienceDynamic Programming
13,088 Citations1966Richard Bellman
The more the authors study the information processing aspects of the mind, the more perplexed and impressed they become, and it will be a very long time before they understand these processes sufficiently to reproduce them.
Management ScienceDecision-Making in a Fuzzy Environment
6,763 Citations1970Richard Bellman, L. A. Zadeh
Machine LearningLearning to Predict by the Methods of Temporal Differences
3,894 Citations1988Richard S. Sutton
This article introduces a class of incremental learning procedures specialized for prediction-that is, for using past experience with an incompletely known system to predict its future behavior, and proves their convergence and optimality for special cases and relate them to supervised-learning methods.
Machine LearningTechnical Note: Q-Learning
3,691 Citations1992Christopher J. Watkins, Peter Dayan
A convergence theorem is presented and proves that Q -learning converges to the optimum action-values with probability 1 so long as all actions are repeatedly sampled in all states and the action- values are represented discretely.
Elsevier eBooksIntegrated Architectures for Learning, Planning, and Reacting Based on Approximating Dynamic Programming
1,351 Citations1990Richard S. Sutton
Results are shown for a simple Dyna-PI system that simultaneously learns by trial and error, learns a world model, and plans optimal routes using the evolving world model and it is shown that Dyna-Q architectures are easy to adapt for use in changing environments.
Artificial IntelligenceLearning to act using real-time dynamic programming
1,109 Citations1995Andrew G. Barto, Steven J. Bradtke +1 more
An algorithm based on dynamic programming, which is called Real-Time DP, is introduced, by which an embedded system can improve its performance with experience and illuminate aspects of other DP-based reinforcement learning methods such as Watkins'' Q-Learning algorithm.
IEEE Transactions on Neural NetworksLearning and tuning fuzzy logic controllers through reinforcements
945 Citations1992H.R. Berenji, P.S. Khedkar
The generalized approximate-reasoning-based intelligent control (GARIC) architecture learns and tunes a fuzzy logic controller even when only weak reinforcement is available; introduces a new conjunction operator in computing the rule strengths of fuzzy control rules; and learns to produce real-valued control actions.
Neural ComputationTD-Gammon, a Self-Teaching Backgammon Program, Achieves Master-Level Play
800 Citations1994Gerald Tesauro
The latest version of TD-Gammon is now estimated to play at a strong master level that is extremely close to the world's best human players.
Machine LearningPractical issues in temporal difference learning
795 Citations1992Gerald Tesauro
It is found that, with zero knowledge built in, the network is able to learn from scratch to play the entire game at a fairly strong intermediate level of performance, which is clearly better than conventional commercial programs, and which surpasses comparable networks trained on a massive human expert data set.
Machine LearningPrioritized Sweeping: Reinforcement Learning with Less Data and Less Time
710 Citations1993Andrew Moore, Christopher G. Atkeson
This work presents a new algorithm, prioritized sweeping, for efficient prediction and control of stochastic Markov systems, which successfully solves large state-space real-time problems with which other methods have difficulty.
National Conference on Artificial IntelligenceProgramming robots using reinforcement learning and teaching
148 Citations1991Long-Ji Lin
This paper presents a general approach to making robots which can improve their performance from experiences as well as from being taught, and develops a simulated learning robot which could learn three moderately complex behaviors and use what was learned in the simulator to operate in the real world quite successfully.
Space shuttle attitude control by reinforcement learning and fuzzy logic
36 Citations2002H.R. Berenji, Robert N. Lea +4 more
It is demonstrated that it is possible to control the pitch, roll, and yaw of the space shuttle within a specified deadband by using fuzzy control rules and to adapt automatically to a reduced error tolerance.