An Analysis of Q-Learning Algorithms with Strategies of Reward Function
Journal Title: International Journal on Computer Science and Engineering - Year 2011, Vol 3, Issue 2
Abstract
Q-Learning is a Reinforcement Learning technique that works by learning an action-value function that gives the expected utility of taking a given action in a given state and following a fixed policy thereafter. One of the strengths of Q-Learning is that it is able to compare the expected utility of the available actions without requiring a model of the environment. Reinforcement Learning is an approach where the agent needs no teacher to learn how to solve a problem. The only signal used by the agent to learn from his actions in reinforcement environment is the so called reward, a number which tells the agent if his last action was good (or) not. Q-Learning is a recent form of Reinforcement Learning algorithm that does not need a model of its environment and can be used on-line. This paper discusses about the different strategies of Q-Learning algorithms and reward function.
Authors and Affiliations
Ms. S. Manju, , Dr. Ms. M. Punithavalli,
Molecular Database Generation for Type 2 Diabetes using Computational Science-Bioinformatics' Tools
In this paper a new algorithm GIGC is proposed which is the modified form of glucose insulin meal GIM model. Diabetes mellitus is one of the worst diseases that are affecting adversely large population. This motivates ma...
Quantum Black Holes and pseudotelepathy in biological organisms
Superposed state of quantum registers can be used to describe inflationary universe. One can speak of a quantum superposition of universes during inflation. It has been proposed by Zizzi that a cosmic consciousness event...
Knowledge Mining of Test Case System
The paper analyzes knowledge mining of the test case System. Widespread use of test case systems and explosive growth of databases require traditional manual data analysis to be coupled with methods for efficient compute...
A Survey on Service Oriented Architecture and Metrics to Measure Coupling
One of the goals of Service-Oriented Computing (SOC) is to design loosely coupled modules or services in the system, so that any changes or modifications to a module or service during maintainability would not effect the...
MAX-MIN ANT OPTIMIZER FOR PROBLEM OF UNCERTAINITY
The real life problems deal with imperfectly specified nowledge and some degree of imprecision, uncertainty or nconsistency is embedded in the problem specification. The well-founded theory of fuzzy sets is a special w...