In an attempt to overcome the limitations of reward-driven representation learning in vision-based reinforcement learning (RL), an unsupervised learning framework referred to as the visual pretraining via contrastive predictive model (VPCPM) is proposed to learn the representations detached from the policy learning. Our method enables the convolutional encoder to perceive the underlying dynamics through a pair of forward and inverse models under the supervision of the contrastive loss, thus resulting in better representations. In experiments with a diverse set of vision control tasks, by initializing the encoders with VPCPM, the performance of state-of-the-art vision-based RL algorithms is significantly boosted, with 44% and 10% improvement for RAD and DrQ at 100 steps, respectively. In comparison to the prior unsupervised methods, the performance of VPCPM matches or outperforms all the baselines. We further demonstrate that the learned representations successfully generalize to the new tasks that share a similar observation and action space.
Keywords: deep reinforcement learning; representation learning; sample efficiency; vision-based deep reinforcement learning.