Hua-Dong Xiong

Individual differences reveal shared computational structure in perceptual decision-making

The paper uses population-level individual differences to discover shared computational components in perceptual decision-making, revealing a six-dimensional structure across datasets.

Human Strategy Adaptation in Reinforcement Learning Resembles Policy Gradient Ascent

This paper introduces DynamicRL, a method to estimate how humans adapt their reinforcement learning strategies over time, showing parameter updates resemble policy gradient ascent.

Deep Learning Improves Parameter Estimation in Reinforcement Learning Models

This study compares parameter estimation methods in reinforcement learning models, finding that deep learning outperforms traditional optimization in reliability and generalizability.