Recurrent Hypernetworks are Surprisingly Strong in Meta-RL
This work addresses sample inefficiency for RL practitioners by showing that simple recurrent baselines with hypernetworks can outperform specialized meta-RL methods, though it is incremental as it builds on prior claims about recurrent networks.
The paper tackles the sample inefficiency problem in deep reinforcement learning by investigating meta-RL methods, finding that combining recurrent networks with hypernetworks achieves the strongest performance among evaluated methods.
Deep reinforcement learning (RL) is notoriously impractical to deploy due to sample inefficiency. Meta-RL directly addresses this sample inefficiency by learning to perform few-shot learning when a distribution of related tasks is available for meta-training. While many specialized meta-RL methods have been proposed, recent work suggests that end-to-end learning in conjunction with an off-the-shelf sequential model, such as a recurrent network, is a surprisingly strong baseline. However, such claims have been controversial due to limited supporting evidence, particularly in the face of prior work establishing precisely the opposite. In this paper, we conduct an empirical investigation. While we likewise find that a recurrent network can achieve strong performance, we demonstrate that the use of hypernetworks is crucial to maximizing their potential. Surprisingly, when combined with hypernetworks, the recurrent baselines that are far simpler than existing specialized methods actually achieve the strongest performance of all methods evaluated. We provide code at https://github.com/jacooba/hyper.