Performance Effectiveness of Multimedia Information Search Using the Epsilon-Greedy Algorithm

Abstract

In the search and retrieval of multimedia objects, it is impractical to either manually or automatically extract the contents for indexing since most of the multimedia contents are not machine extractable, while manual extraction tends to be highly laborious and time-consuming. However, by systematically capturing and analyzing the feedback patterns of human users, vital information concerning the multimedia contents can be harvested for effective indexing and subsequent search. By learning from the human judgment and mental evaluation of users, effective search indices can be gradually developed and built up, and subsequently be exploited to find the most relevant multimedia objects. To avoid hovering around a local maximum, we apply the -greedy method to systematically explore the search space. Through such methodic exploration, we show that the proposed approach is able to guarantee that the most relevant objects can always be discovered, even though initially it may have been overlooked or not regarded as relevant. The search behavior of the present approach is quantitatively analyzed, and closed-form expressions are obtained for the performance of two variants of the -greedy algorithm, namely EGSE-A and EGSE-B. Simulations and experiments on real data set have been performed which show good agreement with the theoretical findings. The present method is able to leverage exploration in an effective way to significantly raise the performance of multimedia information search, and enables the certain discovery of relevant objects which may be otherwise undiscoverable.

Optimizing video click-through rates with bandit algorithms

“…Including improved algorithms, this experiment employed six different algorithms. Based on Mambou's understanding of the Epsilon algorithm, we set it accordingly [9]. B was set to 4.4 based on the distribution of the data.…”

A Brief Study of Deep Reinforcement Learning with Epsilon-Greedy Exploration

“…But, with the introduction of certain level of randomness, the agent, even after having found a solution, will continue to look for other solutions. In epsilon-greedy method, the agent will perform random actions if it satisfies a certain condition [12].…”

“…The Epsilon-Greed Action Selection was then introduced to allow the agent to continue exploration despite having found the solution in the work of Michael Wunder; et al, [12]. It shows how the epsilon-greedy exploration yields higher-than-Nash outcomes.…”

A multi-objective hyper-heuristic algorithm based on adaptive epsilon-greedy selection

“…The Epsilon-greedy method combines the random algorithm and the greedy algorithm to deal with the exploration and exploitation dilemma [16,28]. The main idea of the Epsilon-greedy is to control the utilization rate of the greedy algorithm or the random algorithm through a small probability (smaller than 1) with the aim to make the behavior of the Epsilon-greedy to be greedy most of the time, but random once in a while.…”