CM-DQN: A Value-Based Deep Reinforcement Learning Model to Simulate Confirmation Bias
Journal Title: Engineering and Technology Journal - Year 2024, Vol 9, Issue 07
Abstract
In human decision-making tasks, individuals learn through trials and prediction errors. When individuals learn the task, some are more influenced by good outcomes, while others weigh bad outcomes more heavily. Such confirmation bias can lead to different learning effects. In this study, we propose a new algorithm in Deep Reinforcement Learning, CM-DQN, which applies the idea of different update strategies for positive or negative prediction errors, to simulate the human decision-making process when the task's states are continuous while the actions are discrete. We test in Lunar Lander environment with confirmatory, disconfirmatory bias and non-biased to observe the learning effects. Moreover, we apply the confirmation model in a multi-armed bandit problem (environment in discrete states and discrete actions), which utilizes the same idea as our proposed algorithm, as a contrast experiment to algorithmically simulate the impact of different confirmation bias in decision-making process. In both experiments, confirmatory bias indicates a better learning effect.
Authors and Affiliations
Jiacheng Shen , Lihan Feng,
Keywords
Related Articles
- EP ID EP741373
- DOI 10.47191/etj/v9i07.31
- Views 49
- Downloads 0
Design Modification and Production of a Bicycle Powered By an Internal Combustion Engine
The bicycle serves many purpose .Primarily it is used for transportation. It is also used for sports and leisure. As a means of transportation, there is need to provide more human comforts. This call s for the design mod...
Research on the Evaluation of Water Resources Carrying Capacity in the Central Plains Urban Agglomeration Based on the PS-DR-DP Model
Adequate Water Resource Carrying Capacity (WRCC) is of great significance for the sustainable development of urban agglomerations. Accurately evaluating WRCC is of great significance for the coordinated development of ur...
TOXICITY TEST OF WASTE OIL BEFORE AND AFTER TREATMENT USING PHYTOREMEDIATION ON BIOINDICATORS
Silugonggo River is a river that crosses Juwana District, Pati Regency, Central Java, which empties into the Java Sea. Industrial activities and workshops around the Silugonggo River cause river water to become polluted...
EVOLUTION OF SONAR SURVEY SYSTEMS FOR SEA FLOOR STUDIES.
Approximately 71% of our planet is covered with oceans. It is also known that oceans are the last frontiers for the mankind’s survival and therefore it becomes pertinent that they are studied in great details. It has bee...
Analysis of Advantages Data on Hijri Year Compared AD Year through Wind Speed Climate Modeling
The Gamma and Weibull distribution models were used for modeling wind speed data in the AD years and Hijri years. This study aims to determine the best model for wind speed data using Gamma and Weibull distributions. The...