Acceleration of Actor-Critic Deep Reinforcement Learning for Visual Grasping by State Representation Learning Based on a Preprocessed Input Image
Taewon Kim,Yeseong Park,Youngbin Park,Sang Hyoung Lee,Il Hong Suh,Taewon Kim,Yeseong Park,Youngbin Park,Sang Hyoung Lee,Il Hong Suh
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...
