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 27
- Downloads 0
SECURING DIGITAL INFORMATION THROUGH IMAGE WATERMARKING WITH LSB ALGORITHM: A COMPREHENSIVE OVERVIEW AND IMPLEMENTATION USING MATLAB
Over the years, researchers have been intrigued by the concept of information hiding, which involves concealing secrets and protecting information. Digital watermarking and steganography tools have been developed to achi...
Design and Development Performance Assessment System for Medical Staff Implementing the Regulations of the Indonesian Ministry of Health (Case Study: Arifin Achmad General Hospital, Riau Province)
The difficulty in conducting performance assessments of medical staff is the background for the Arifin Achmad Regional General Hospital (RSUD) to implement performance assessment standardization which refers to the techn...
STUDY OF THE CHOICE OF FREIGHT TRANSPORTATION MODES BETWEEN TRUCKS AND RIVER TRANSPORTATION ON BANJARMASIN – MUARA TEWEH ROUTE
Transportation is a fundamental factor in the life of a nation and state, has a function as a driver and support for development. Users of transportation services are the wider community who need transportation services....
EFFECTS OF THE ACQUISITION AND CONVERSION OF AGRICULTURAL LAND USE PURPOSES ON THE LIVELIHOODS OF HOUSEHOLD AT THE EXTENDED BAC SON ROAD PROJECT, THAI NGUYEN CITY, THAI NGUYEN PROVINCE
The study focuses on assessing the economic risks of the acquisition and conversion of agricultural land use purposes of the extended Bac Son road project in Thai Nguyen city. Research using methods such as: document syn...
The Advancements Blockchain has had on the Financial Services Industry
The financial services industry handles transactions amounting to trillions of dollars daily, necessitating a focus on cost-efficiency, transparency, and security. Prior to the integration of blockchain technology, inter...