My research interests are in the area of machine learning for speech, language, and sound processing. I am particularly interested in multimodality and unsupervised ...

There are two ways numbers are represented internally - integers and floating point numbers. Even though the numbers 1 and 1.0 have the same value their internal representation are very different.

Placed online: Tuesday, November 11 Due: no later than 11 pm, Thursday, December 5 (You CAN use slip days on assignment 11 if you have some left. Some semester do not allow the use of slip days when ...

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 ...

Grounded Action Transformation for Robot Learning in Simulation. Josiah Hanna and Peter Stone. @InProceedings{AAAI17-Hanna, author = {Josiah Hanna and Peter Stone}, title = {Grounded Action ...

TEXPLORE: Real-Time Sample-Efficient Reinforcement Learning for Robots. Todd Hester and Peter Stone. Machine Learning, 90(3):385–429, 2013.

Two Stock-Trading Agents: Market Making and Technical Analysis. Yi Feng, Ronggang Yu, and Peter Stone. In Peyman Faratin, David C. Parkes, Juan A. Rodriguez-Aguilar, and William E. Walsh, editors, ...

Mobile Robot Planning using Action Language BC with an Abstraction Hierarchy. Shiqi Zhang, Fangkai Yang, Piyush Khandelwal, and Peter Stone. In Proceedings of the 13th International Conference on ...

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 ...

Learning Perceptual Hallucination for Multi-Robot Navigation in Narrow Hallways. Jinsoo Park, Xuesu Xiao, Garrett Warnell, Harel Yedidsion, and Peter Stone. In Proceedings of the 2023 IEEE ...

Adding Influencing Agents to a Flock. Katie Genter and Peter Stone. @InProceedings{AAMAS16-katie, author = {Katie Genter and Peter Stone}, title = {Adding Influencing Agents to a Flock}, booktitle = ...

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 ...