Proposed a new method for constructing multiagent reinforcement learning experiments and designed an experiment setup that is inviting to social scientists with minimal background in machine learning.
Research Experience
Involved in developing biologically-inspired and cognitively plausible AI systems; developed machine-learning processes based on current understandings of complex cognitive processes (including memory formation and retrieval, affective emotional states, and biases in social interaction); led the design and implementation of Sorrel, a novel approach to multiagent RL environment building.
Background
Research interests include developing multi-agent neural network models grounded in cutting-edge approaches from neuroscience, psychology, sociology, history, and cultural anthropology. Aiming to illuminate the cognitive processes that enable people to navigate fundamental aspects of cooperation and competition within and between social groups.
Miscellany
The research also involves analyzing behaviors from the neuron level to nation-state level, aiming to understand individual choices, group behaviors, or societal outcomes by integrating empirically-informed insights across these levels.