While improvements in deep learning architectures have played a crucial role in improving the state of supervised and unsupervised learning in computer vision and natural language processing, neural network architecture choices for reinforcement learning remain relatively under-explored. We take inspiration from successful architectural choices in computer vision and generative modelling, and investigate the use of deeper networks and dense connections for reinforcement learning on a variety of simulated robotic learning benchmark environments. Our findings reveal that current methods benefit significantly from dense connections and deeper networks, across a suite of manipulation and locomotion tasks, for both proprioceptive and image-based observations. We hope that our results can serve as a strong baseline and further motivate future research into neural network architectures for reinforcement learning. The project website with code is at this link https://sites.google.com/view/d2rl/home.
@article{arxiv.2010.09163,
title = {D2RL: Deep Dense Architectures in Reinforcement Learning},
author = {Samarth Sinha and Homanga Bharadhwaj and Aravind Srinivas and Animesh Garg},
journal= {arXiv preprint arXiv:2010.09163},
year = {2020}
}
Comments
NeurIPS 2020 Deep RL Workshop. Preprint. Under review