Taehyun Cho

I am a Ph.D. in Electrical and Computer Engineering from the Cognitive Machine Learning Laboratory at Seoul National University, advised by Jungwoo Lee. My research focuses on reinforcement learning, human-aligned sequential decision-making, and uncertainty-aware learning. I received my B.S. in Mathematics from Korea University.

Personal Interest

Strategic Games:
I am a high-level Teamfight Tactics(TFT) player, having ranked within the top 9 during a competitive season. I treat strategic games as experimental laboratories for studying decision-making under uncertainty. Competitive multi-agent environments such as TFT require continuous adaptation, opponent modeling, and risk-sensitive planning. I often reflect on my own gameplay to analyze how strategies are formed, refined, and adjusted in response to stochastic dynamics and strategic interaction. I am particularly interested in formalizing how such strategies emerge in competitive settings and in translating these principles into reinforcement learning agents operating under uncertainty.

Behavioral Economics and Cognitive Science:
Behavioral economics and cognitive science play a central role in how I think about human decision-making. Many reinforcement learning formulations focus primarily on maximizing expected return, abstracting away inference-time constraints and bounded rationality. I am interested in understanding how human biases, risk perception, and cognitive limitations shape actual decisions. This perspective motivates my research on modeling human-aligned decision processes that go beyond expectation maximization and instead account for uncertainty, regret, and subjective evaluation of outcomes.

Philosophy:
Since 2020, I have participated in regular philosophical discussions through a group called "Sunday Salon". Our discussions began with themes inspired by the French "Baccalauréat" examination topics and have gradually expanded toward questions related to artificial intelligence and its societal implications. These discussions have shaped how I think about human uniqueness, responsibility, and counterfactual reflection. I am particularly interested in understanding what aspects of human reasoning—such as regret, moral evaluation, and narrative self-reflection—remain difficult to formalize, and how these elements might inform the development of human-aligned AI systems.

Research Interest

My academic research focuses on sequential decision-making under uncertainty, particularly in the context of human feedback. I have extensively studied distributional reinforcement learning (distRL), reinforcement learning from human feedback (RLHF), and regret analysis, aiming to bridge theory and practice.

Drawing inspiration from how humans make decisions, I aim to develop mathematical models and optimize for human-in-the-loop systems, uncovering both theoretical insights and practical algorithms for robust decision-making. Currently, I’m interested in reasoning LLM agents and regret-based decision theory.

I’m actively looking for research scientist or postdoctoral opportunities in theoretical foundations of reinforcement learning or reasoning LLM research.