-
Deep Reinforcement Learning: An Overview
In recent years, a specific machine learning method called deep learning...
read it
-
Deep Convolutional Neural Network Design Patterns
Recent research in the deep learning field has produced a plethora of ne...
read it
-
Towards Deeper Generative Architectures for GANs using Dense connections
In this paper, we present the result of adopting skip connections and de...
read it
-
SoftGym: Benchmarking Deep Reinforcement Learning for Deformable Object Manipulation
Manipulating deformable objects has long been a challenge in robotics du...
read it
-
Latent Attention Networks
Deep neural networks are able to solve tasks across a variety of domains...
read it
-
A Perspective on Deep Learning for Molecular Modeling and Simulations
Deep learning is transforming many areas in science, and it has great po...
read it
-
Unsupervisedly Learned Representations: Should the Quest be Over?
There exists a Classification accuracy gap of about 20 methods of genera...
read it
D2RL: Deep Dense Architectures in Reinforcement Learning
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.
READ FULL TEXT
Comments
There are no comments yet.