29 citations · 39 across the 4 of their papers we have counts for
4 papers
Trajectory Planning with Deep Reinforcement Learning in High-Level Action Spaces
Kyle R. Williams, Rachel Schlossman, Daniel Whitten +8
This paper presents a technique for trajectory planning based on continuously parameterized high-level actions (motion primitives) of variable duration. This technique leverages de…
RAPDARTS: Resource-Aware Progressive Differentiable Architecture Search
Sam Green, Craig M. Vineyard, Ryan Helinski +1
Early neural network architectures were designed by so-called "grad student descent". Since then, the field of Neural Architecture Search (NAS) has developed with the goal of algor…
Distillation Strategies for Proximal Policy Optimization
Sam Green, Craig M. Vineyard, Çetin Kaya Koç
Vision-based deep reinforcement learning (RL) typically obtains performance benefit by using high capacity and relatively large convolutional neural networks (CNN). However, a larg…
Visual Diagnostics for Deep Reinforcement Learning Policy Development
Jieliang Luo, Sam Green, Peter Feghali +2
Modern vision-based reinforcement learning techniques often use convolutional neural networks (CNN) as universal function approximators to choose which action to take for a given v…