Reinforcement learning agents that have not been seen during training must be robust in test environments. However, the generalization problem is challenging to solve in reinforcement learning using high-dimensional images as the input. The addition of a self-supervised learning framework with data augmentation in the reinforcement learning architecture can promote generalization to a certain extent. However, excessively large changes in the input images may disturb reinforcement learning. Therefore, we propose a contrastive learning method that can help manage the trade-off relationship between the performance of reinforcement learning and auxiliary tasks against the data augmentation strength. In this framework, strong augmentation does not disturb reinforcement learning and instead maximizes the auxiliary effect for generalization. Results of experiments on the DeepMind Control suite demonstrate that the proposed method effectively uses strong data augmentation and achieves a higher generalization than the existing methods.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC10222541PMC
http://dx.doi.org/10.3390/s23104946DOI Listing

Publication Analysis

Top Keywords

reinforcement learning
28
data augmentation
12
learning
10
strong augmentation
8
augmentation reinforcement
8
disturb reinforcement
8
reinforcement
7
augmentation
5
c2rl convolutional-contrastive
4
convolutional-contrastive learning
4

Similar Publications

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!