When Should We Prefer State-to-Visual DAgger Over Visual Reinforcement Learning?
December 18, 2024 Β· Declared Dead Β· π AAAI Conference on Artificial Intelligence
"No code URL or promise found in abstract"
Evidence collected by the PWNC Scanner
Authors
Tongzhou Mu, Zhaoyang Li, StanisΕaw Wiktor Strzelecki, Xiu Yuan, Yunchao Yao, Litian Liang, Hao Su
arXiv ID
2412.13662
Category
cs.CV: Computer Vision
Cross-listed
cs.AI,
cs.LG,
cs.RO
Citations
5
Venue
AAAI Conference on Artificial Intelligence
Last Checked
5 months ago
Abstract
Learning policies from high-dimensional visual inputs, such as pixels and point clouds, is crucial in various applications. Visual reinforcement learning is a promising approach that directly trains policies from visual observations, although it faces challenges in sample efficiency and computational costs. This study conducts an empirical comparison of State-to-Visual DAgger, a two-stage framework that initially trains a state policy before adopting online imitation to learn a visual policy, and Visual RL across a diverse set of tasks. We evaluate both methods across 16 tasks from three benchmarks, focusing on their asymptotic performance, sample efficiency, and computational costs. Surprisingly, our findings reveal that State-to-Visual DAgger does not universally outperform Visual RL but shows significant advantages in challenging tasks, offering more consistent performance. In contrast, its benefits in sample efficiency are less pronounced, although it often reduces the overall wall-clock time required for training. Based on our findings, we provide recommendations for practitioners and hope that our results contribute valuable perspectives for future research in visual policy learning.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
π Similar Papers
In the same crypt β Computer Vision
π
π
Old Age
π
π
Old Age
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
π
π
Old Age
SSD: Single Shot MultiBox Detector
π
π
Old Age
Squeeze-and-Excitation Networks
π
π
Old Age
Fast R-CNN
π
π
Old Age
Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization
Died the same way β π» Ghosted
R.I.P.
π»
Ghosted
Federated Learning: Strategies for Improving Communication Efficiency
R.I.P.
π»
Ghosted
In-Datacenter Performance Analysis of a Tensor Processing Unit
R.I.P.
π»
Ghosted
Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning
R.I.P.
π»
Ghosted