Analyzing and Overcoming Degradation in Warm-Start Reinforcement Learning
Benjamin Wexler,Elad Sarafian,Sarit Kraus,Benjamin Wexler,Elad Sarafian,Sarit Kraus
Reinforcement Learning (RL) for robotic applications can benefit from a warm-start where the agent is initialized with a pretrained behavioral policy. However, when transitioning to RL updates, degradation in performance can occur, which may compromise the robot's safety. This degradation, which constitutes an inability to properly utilize the pretrained policy, is attributed to extrapolation erro...