The State of Sparse Training in Deep Reinforcement Learning
This work addresses the under-explored problem of sparse training in DRL for researchers and practitioners, but it is incremental as it applies known methods to a new domain.
The paper systematically investigates applying existing sparse training techniques to deep reinforcement learning (DRL) agents and environments, finding that sparse networks outperform dense networks with the same parameter count, corroborating results from computer vision.
The use of sparse neural networks has seen rapid growth in recent years, particularly in computer vision. Their appeal stems largely from the reduced number of parameters required to train and store, as well as in an increase in learning efficiency. Somewhat surprisingly, there have been very few efforts exploring their use in Deep Reinforcement Learning (DRL). In this work we perform a systematic investigation into applying a number of existing sparse training techniques on a variety of DRL agents and environments. Our results corroborate the findings from sparse training in the computer vision domain - sparse networks perform better than dense networks for the same parameter count - in the DRL domain. We provide detailed analyses on how the various components in DRL are affected by the use of sparse networks and conclude by suggesting promising avenues for improving the effectiveness of sparse training methods, as well as for advancing their use in DRL.