Hard-Thresholding Meets Evolution Strategies in Reinforcement Learning

arXiv:2405.01615v1 Announce Type: cross
Abstract: Evolution Strategies (ES) have emerged as a competitive alternative for model-free reinforcement learning, showcasing exemplary performance in tasks like Mujoco and Atari. Notably, they shine in scenarios with imperfect reward functions, making them invaluable for real-world applications where dense reward signals may be elusive. Yet, an inherent assumption in ES, that all input features are task-relevant, poses challenges, especially when confronted with irrelevant features common in real-world problems. This work scrutinizes this limitation, particularly focusing …

abstract alternative applications arxiv cs.lg cs.ne evolution exemplary free functions making performance reinforcement reinforcement learning shine strategies tasks them thresholding type world