Pretrained Encoders are All You Need
This work addresses data and compute efficiency for reinforcement learning practitioners, but it is incremental as it applies existing pretrained methods to a new domain.
The paper tackled the challenge of data-efficiency and generalization in deep reinforcement learning by using pretrained image representations and spatio-temporal attention for state representation learning in Atari, showing that these representations perform on par with state-of-the-art self-supervised methods trained on domain-specific data.
Data-efficiency and generalization are key challenges in deep learning and deep reinforcement learning as many models are trained on large-scale, domain-specific, and expensive-to-label datasets. Self-supervised models trained on large-scale uncurated datasets have shown successful transfer to diverse settings. We investigate using pretrained image representations and spatio-temporal attention for state representation learning in Atari. We also explore fine-tuning pretrained representations with self-supervised techniques, i.e., contrastive predictive coding, spatio-temporal contrastive learning, and augmentations. Our results show that pretrained representations are at par with state-of-the-art self-supervised methods trained on domain-specific data. Pretrained representations, thus, yield data and compute-efficient state representations. https://github.com/PAL-ML/PEARL_v1