D2RL: Deep Dense Architectures in Reinforcement Learning

by   Samarth Sinha, et al.

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.


page 13

page 15


Evaluating Vision Transformer Methods for Deep Reinforcement Learning from Pixels

Vision Transformers (ViT) have recently demonstrated the significant pot...

Deep Reinforcement Learning: An Overview

In recent years, a specific machine learning method called deep learning...

Pretraining the Vision Transformer using self-supervised methods for vision based Deep Reinforcement Learning

The Vision Transformer architecture has shown to be competitive in the c...

Deep Convolutional Neural Network Design Patterns

Recent research in the deep learning field has produced a plethora of ne...

Open-Ended Reinforcement Learning with Neural Reward Functions

Inspired by the great success of unsupervised learning in Computer Visio...

Latent Attention Networks

Deep neural networks are able to solve tasks across a variety of domains...

Visual Diagnostics for Deep Reinforcement Learning Policy Development

Modern vision-based reinforcement learning techniques often use convolut...