Taylor A. Kessler Faulkner

2 accepted papers

2023

Using Learning Curve Predictions to Learn from Incorrect Feedback

Taylor A. Kessler Faulkner, Andrea L. Thomaz

ICRA 2023poster

Robots can incorporate data from human teachers when learning new tasks. However, this data can often be noisy, which can cause robots to learn slowly or not at all. One method for learning from human teachers is Human-in-the-loop Reinforcement Learning (HRL), which can combine information from both…

Cited by 1 Source ↗Scholar ↗

2020

Interactive Reinforcement Learning with Inaccurate Feedback

Taylor A. Kessler Faulkner, Elaine Schaertl Short, Andrea L. Thomaz

ICRA 2020poster

Interactive Reinforcement Learning (RL) enables agents to learn from two sources: rewards taken from observations of the environment, and feedback or advice from a secondary critic source, such as human teachers or sensor feedback. The addition of information from a critic during the learning proces…

Cited by 30 Source ↗Scholar ↗