Jacob Adkins — accepted AI-conference papers

2024

A Method for Evaluating Hyperparameter Sensitivity in Reinforcement Learning

Jacob Adkins, Michael Bowling, Adam White

NeurIPS 2024poster

The performance of modern reinforcement learning algorithms critically relies on tuning ever increasing numbers of hyperparameters. Often, small changes in a hyperparameter can lead to drastic changes in performance, and different environments require very different hyperparameter settings to achiev…

Cited by 2 Source ↗PDF ↗code ↗Scholar ↗

2023

All the Feels: A Dexterous Hand With Large-Area Tactile Sensing

Raunaq M. Bhirangi, Abigail DeFranco, Jacob Adkins, Carmel Majidi, Abhinav Gupta, Tess Lee Hellebrekers +1

RA-L 2023

High cost and lack of reliability have precluded the widespread adoption of dexterous hands in robotics. Furthermore, the lack of a viable tactile sensor capable of sensing over the entire area of the hand impedes the rich, low-level feedback that would improve the learning of dexterous manipulation

Cited by 22 Source ↗Scholar ↗