Title | ||
---|---|---|
Acceleration of Actor-Critic Deep Reinforcement Learning for Visual Grasping by State Representation Learning Based on a Preprocessed Input Image |
Abstract | ||
---|---|---|
For robotic grasping tasks with diverse target objects, some deep learning-based methods have achieved state-of-the-art results using direct visual input. In contrast, actor-critic deep reinforcement learning (RL) methods typically perform very poorly when applied to grasp diverse objects, especially when learning from raw images and sparse rewards. To render these RL techniques feasible for visio... |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/IROS51168.2021.9635931 | 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) |
Keywords | DocType | ISSN |
Representation learning,Training,Learning systems,Visualization,Data preprocessing,Grasping,Reinforcement learning | Conference | 2153-0858 |
ISBN | Citations | PageRank |
978-1-6654-1714-3 | 0 | 0.34 |
References | Authors | |
0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Taewon Kim | 1 | 0 | 0.34 |
Yeseong Park | 2 | 0 | 0.34 |
Youngbin Park | 3 | 4 | 5.85 |
Sang Hyoung Lee | 4 | 0 | 0.34 |
Il Hong Suh | 5 | 0 | 0.34 |