“D2RL: Deep Dense Architectures in Reinforcement Learning”, Samarth Sinha, Homanga Bharadhwaj, Aravind Srinivas, Animesh Garg2020-10-19 (MLP NN, model-free RL)⁠:

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 modeling, 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 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.