Towards Practical Multi-Object Manipulation using Relational Reinforcement Learning
December 23, 2019 ยท Declared Dead ยท ๐ IEEE International Conference on Robotics and Automation
"No code URL or promise found in abstract"
Evidence collected by the PWNC Scanner
Authors
Richard Li, Allan Jabri, Trevor Darrell, Pulkit Agrawal
arXiv ID
1912.11032
Category
cs.RO: Robotics
Cross-listed
cs.AI,
cs.LG
Citations
121
Venue
IEEE International Conference on Robotics and Automation
Last Checked
3 months ago
Abstract
Learning robotic manipulation tasks using reinforcement learning with sparse rewards is currently impractical due to the outrageous data requirements. Many practical tasks require manipulation of multiple objects, and the complexity of such tasks increases with the number of objects. Learning from a curriculum of increasingly complex tasks appears to be a natural solution, but unfortunately, does not work for many scenarios. We hypothesize that the inability of the state-of-the-art algorithms to effectively utilize a task curriculum stems from the absence of inductive biases for transferring knowledge from simpler to complex tasks. We show that graph-based relational architectures overcome this limitation and enable learning of complex tasks when provided with a simple curriculum of tasks with increasing numbers of objects. We demonstrate the utility of our framework on a simulated block stacking task. Starting from scratch, our agent learns to stack six blocks into a tower. Despite using step-wise sparse rewards, our method is orders of magnitude more data-efficient and outperforms the existing state-of-the-art method that utilizes human demonstrations. Furthermore, the learned policy exhibits zero-shot generalization, successfully stacking blocks into taller towers and previously unseen configurations such as pyramids, without any further training.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
๐ Similar Papers
In the same crypt โ Robotics
๐
๐
Old Age
R.I.P.
๐ป
Ghosted
ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras
R.I.P.
๐ป
Ghosted
VINS-Mono: A Robust and Versatile Monocular Visual-Inertial State Estimator
R.I.P.
๐ป
Ghosted
ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM
R.I.P.
๐ป
Ghosted
Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World
R.I.P.
๐ป
Ghosted
Past, Present, and Future of Simultaneous Localization And Mapping: Towards the Robust-Perception Age
Died the same way โ ๐ป Ghosted
R.I.P.
๐ป
Ghosted
Language Models are Few-Shot Learners
R.I.P.
๐ป
Ghosted
PyTorch: An Imperative Style, High-Performance Deep Learning Library
R.I.P.
๐ป
Ghosted
XGBoost: A Scalable Tree Boosting System
R.I.P.
๐ป
Ghosted