The University of Texas at Austin
- Offer Profile
- I am the founder and director
of the Learning Agents Research Group (LARG) within the Artificial
Intelligence Laboratory in the Department of Computer Science at The
University of Texas at Austin.
My main research interest in
AI is understanding how we can best create complete intelligent agents. I
consider adaptation, interaction, and embodiment to be essential capabilites
of such agents. Thus, my research focuses mainly on machine learning, multiagent
systems, and robotics. To me, the most exciting research topics are those
inspired by challenging real-world problems. I believe that complete
successful research includes both precise, novel algorithms and fully
implemented and rigorously evaluated applications.
- My application domains have included robot soccer,
autonomous bidding agents, autonomous vehicles, autonomic computing, and
My long-term research goal is to create complete,
robust, autonomous agents that can learn to interact with other intelligent
agents in a wide range of complex, dynamic environments.
- A large part of the lab's research focus is on developing
new reinforcement learning algorithms with a particular focus on scaling up
to large-scale applications.
- One main theme of the lab is the study of interactions
among independent autonomous agents (including robots), be they teammates,
adversaries, or neither. Some of our research on this topic contributes to
and makes use of game theory.
- One of the main application domains used throughout the
lab is robot soccer, both in simulation and on real robots. We have won
multiple RoboCup championships.
- Another main application domain is autonomous trading
agents, including supply chain management, ad auctions, and mechanism
design. We have won multiple Trading Agent Competitions.
Autonomous Traffic Management
- We introduced a novel, efficient multiagent mechanism for
future autonomous vehicles to navigate intersections.
- We have a full-size autonomous vehicle that we use to
study autonomous driving in the real world.
Teaching an Agent Manually via Evaluative Reinforcement
- The TAMER project seeks to create agents which can be
effectively taught behaviors by lay people using positive and negative
feedback signals (akin to "shaping" by reward and punishment in animal
- We develop algorithms suitable for real-time visual
sensing of the physical world on mobile robots.
- We have developed algorithms from transfering knowledge
from a previously learned task to a similar, but different, new learning
task. We focus particularly on reinforcement learning tasks.
Learned Robot Walking
- We enabled an Aibo robot to learn to walk faster than was
General Game Playing
- We participated successfully in the first few general
game playing competitions.
- We are developing machine learning approaches for
computer systems applications.
- We finished in 2nd place in the 2007 RoboCup@Home
- We have developed methods for robots to autonomously
discover models of their own sensor and actuators.
Predictive State Representations
- We have contributed to the literature on representating
an agent's state entirely via predictions of its future sensations as a
function of its possible actions. Thus it does not need to reason explicitly
- My Ph.D. thesis introduced a general hierarchical machine
learning paradigm by which complex tasks can be learned via several
interacting learned layers.
- My first research as a Ph.D. student was within the area
of classical AI planning. Some of our current research falls in the area of
modern planning and scheduling