Research Areas
This page is the index of my papers. It is designed to help readers quickly find work on reasoning agents, gaming agents, embodied agents, open-ended learning, multi-agent reinforcement learning, social simulation, AI economics, generative simulacra, mechanism design, and emergent communication.
Work on competitive language agents, reasoning agents, gaming agents, embodied agents, long-context decision making, and benchmarks for strategic play in complex adversarial environments. This includes the first Pokemon battling paper at ICML, ICLR, or NeurIPS and a broader benchmark program that treats Pokemon as a serious machine learning testbed.
Work on large populations of language agents, social simulation, policy interventions, and mechanism design in synthetic social and economic systems.
Work on communication protocols in cooperative and social multi-agent learning, with an emphasis on interpretability, sparsity, and human-agent teaming.
Earlier work on improving kinodynamic planning for autonomous vehicles with learned controllers.
Generative simulacra
This paper studies large populations of language agents and uses them to analyze policy and mechanism design questions in multi-agent generative simulacra, social simulation, and AI economics.
Agents in games
A competition benchmark and evaluation harness that turns Pokemon into a durable machine learning testbed for long-context learning, reasoning agents, embodied agents, and strategic decision making.
Agents in games
The first Pokemon battling paper at ICML, ICLR, or NeurIPS. An ICML Spotlight paper that establishes competitive Pokemon battling as a top-tier machine learning setting for reasoning agents and strategic language agents.
Agents in games
A benchmark and empirical test harness for evaluating competitive multi-agent reinforcement learning in structured adversarial environments.
Emergent communication
This paper examines how emergent communication shapes social learning dynamics in multi-agent reinforcement learning.
Emergent communication
This paper studies how to learn sparse communication protocols without discarding information needed for coordination.
Emergent communication
This paper focuses on making learned emergent communication more interpretable for human-agent teams.
Robotics and planning
This paper improves kinodynamic planning for vehicles by combining classical planning with learned goal-reaching controllers.