www.cs.utexas.edu2d
The Perils of Trial-and-Error Reward Design: Misdesign through Overfitting and Invalid Task Specifications
In reinforcement learning (RL), a reward function that aligns exactly with a task's true performance metric is often sparse. For example, a true task metric might encode a reward of 1 upon success and ...
www.cs.utexas.edu2d
Generative Adversarial Imitation from Observation
Imitation from observation (IfO) is the problem of learning directly from state-only demonstrations without having access to the demonstrator's actions.The lack of action information both ...
www.cs.utexas.edu5d
Research Poster Printing Services
At UTCS Publications Office, we operate in alignment with the academic calendar, including closures during holidays and breaks when no classes are held. Please be aware of these closures when planning ...
www.cs.utexas.edu5d
Representing Knowledge of Large-Scale Space (1977)
This dissertation presents a model of the knowledge a person has about the spatial structure of a large-scale environment: the ``cognitive map.'' The functions of the cognitive map are to assimilate ...
www.cs.utexas.edu6d
My Course Schedule
CS 309: AI Literacy (Essentials of AI) Web-based (Zoom) - GDC TTH 9:30am-11:00am Peter Stone ...
www.cs.utexas.edu6d
Michael Quinlan
Michael researches various aspects of robotic systems, including motion, vision and localization. He currently teaches a class on Autonomous Vehicles and competes as part of the Austin Villa team at ...
www.cs.utexas.edu6d
Multi-Robot Human Guidance: Human Experiments and Multiple Concurrent Requests
In the multi-robot human guidance problem, a centralized controller makes use of multiple robots to provide navigational assistance to a human in order to reach a goal location. Previous work used ...
www.cs.utexas.edu6d
Raymond J. Mooney
Professor of Computer Sciences, University of Texas at Austin. B.S. in Computer Engineering, University of Illinois at Urbana/Champaign, 1983 M.S. in Computer Science, University of Illinois at Urbana ...
www.cs.utexas.edu7d
TAMER: Training an Agent Manually via Evaluative Reinforcement
Though computers have surpassed humans at many tasks, especially computationally intensive ones, there are many tasks for which human expertise remains necessary and/or useful. For such tasks, it is ...
www.cs.utexas.edu7d
Reinforcement Learning from Simultaneous Human and MDP Reward
Reinforcement Learning from Simultaneous Human and MDP Reward. W. Bradley Knox and Peter Stone. In Proceedings of the 11th International Conference on Autonomous Agents and Multiagent Systems (AAMAS), ...
www.cs.utexas.edu7d
The right music at the right time: adaptive personalized playlists based on sequence modeling
The right music at the right time: adaptive personalized playlists based on sequence modeling. Elad Liebman, Maytal Saar-Tsechansky, and Peter Stone Peter Stone. Management Information Systems ...
www.cs.utexas.edu7d
Protecting Against Evaluation Overfitting in Empirical Reinforcement Learning
Protecting Against Evaluation Overfitting in Empirical Reinforcement Learning. Shimon Whiteson, Brian Tanner, Matthew E. Taylor, and Peter Stone. In IEEE Symposium on Adaptive Dynamic Programming and ...