Bilevel optimization (BO) is useful for solving a variety of important machine learning problems including but not limited to hyperparameter optimization, meta-learning, continual learning, and ...

Recent work has shown that deep neural networks are capable ofapproximating both value functions and policies in reinforcementlearning domains featuring continuous state and actionspaces. However, to ...

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 ...

Gaussian processes for sample efficient reinforcement learning with RMAX-like exploration. Tobias Jung and Peter Stone. @InProceedings{ECML10-jung, author = "Tobias Jung and Peter Stone", title = ...

Our students and faculty are changing the world through their contributions to computing education, research, and industry. These awards received by members of the UT Computer Science community make ...

Artificial Intelligence and Life in 2030. Peter Stone, Rodney Brooks, Erik Brynjolfsson, Ryan Calo, Oren Etzioni, Greg Hager, Julia Hirschberg, Shivaram ...

Transfer Learning for Reinforcement Learning Domains: A Survey. Matthew E. Taylor and Peter Stone. Journal of Machine Learning Research, 10(1):1633–1685, 2009.

Multiagent Traffic Management: A Reservation-Based Intersection Control Mechanism. Kurt Dresner and Peter Stone. In The Third International Joint Conference on Autonomous Agents and Multiagent Systems ...

To Teach or not to Teach? Decision Making Under Uncertainty in Ad Hoc Teams. Peter Stone and Sarit Kraus. In The Ninth International Conference on Autonomous Agents and Multiagent Systems (AAMAS), ...

Classically, imitation learning algorithms have been developed for idealized situations, e.g., the demonstrations are often required to be collected in the exact same environment and usually include ...

Austin Robot Technology's (ART's) entry in the DARPA Urban Challenge has two main goals. First and foremost,the team aims to create a fully autonomous vehicle that is capable of safely and robustly ...

Developing the next generation of household robot helpers requires combining locomotion and interaction capabilities, which is generally referred to as mobile manipulation (MoMa). MoMa tasks are ...