Augmentation Curriculum Learning For Generalization in RL
ICLR 2023(2023)
摘要
Many Reinforcement Learning tasks rely solely on pixel-based observations of
the environment. During deployment, these observations can fall victim to visual
perturbations and distortions, causing the agent’s policy to significantly degrade
in performance. This motivates the need for robust agents that can generalize in
the face of visual distribution shift. One common technique for doing this is to ap-
ply augmentations during training; however, it comes at the cost of performance.
We propose Augmentation Curriculum Learning a novel curriculum learning ap-
proach that schedules augmentation into training into a weak augmentation phase
and strong augmentation phase. We also introduce a novel visual augmentation
strategy that proves to aid in the benchmarks we evaluate on. Our method achieves
state-of-the-art performance on Deep Mind Control Generalization Benchmark.
更多查看译文
关键词
reinforcement learning,generalization,pixel-based RL,embodied learning
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要