H Thomas Pouncy

Doctoral Researcher

Harvard University

About me

I’m a doctoral researcher currently working with Sam Gershman in the Psychology Department at Harvard University. I’m interested in understanding the inductive biases that drive human learning in naturalistically complex decision-making domains. In particular my work focuses on modeling human learning in video games using a variety of Bayesian inference and reinforcement learning techniques. Ultimately I hope to apply the results of my research to real world classroom environments to improve curriculum design and assessment for traditionally underserved populations.


  • Education
  • Computational modeling
  • Model-based reinforcement learning
  • Data architecture

Recent Publications

Quickly discover relevant content by filtering publications.

Inductive biases in theory-based reinforcement learning

Inductive biases lie at the core of human learning efficiency. Making assumptions about task structure allows us to better predict task …

Human-Level Reinforcement Learning through Theory-Based Modeling, Exploration, and Planning

Reinforcement learning (RL) studies how an agent comes to achieve reward in an environment through interactions over time. Recent …

What Is the Model in Model-Based Planning?

Flexibility is one of the hallmarks of human problem-solving. In everyday life, people adapt tochanges in common tasks with little to …

Discovering social groups via latent structure learning

Humans form social coalitions in every society on earth, yet we know very little about how social group boundaries are learned and …

Human learning in Atari

Atari games are an excellent testbed for studying intelligent behavior, as they offer a range of tasks that differ widely in their …


Bayesian Inference


Web development





  • 52 Oxford Street, Cambridge, MA 02138