Babak Nadjar Araabi

Deformed Probability Estimation in Goal-Directed reinforcement learning model explains anxious-depression dimensions of psychiatric disorders

This paper introduces a deformation in probability estimation to a reinforcement learning model, linking it to anxious-depression symptoms in psychiatric disorders.

Optimal Reinforcement Learning with Asymmetric Updating in Volatile Environments: a Simulation Study

This study compares two reinforcement learning models in volatile environments, finding that separate reward and punishment learning rates improve performance, with higher reward learning rates being more beneficial.

An Information-based approach to handle various types of uncertainty in Fuzzy Bodies of Evidence

This paper introduces a generalized dissimilarity measure for fuzzy bodies of evidence to handle all types of uncertainty, demonstrating its effectiveness through experiments.

Better than maximum likelihood estimation of model-based and model-free learning style

The paper proposes a k-nearest neighbor method to improve parameter estimation in reinforcement learning models, showing better reliability than maximum likelihood approaches.