BROWSE
Detail
Conference Paper
An Experimental Study of Collaborative Robot Manipulation via Multi-Agent Reinforcement Learning
Cited - time in 
Share 
Share
- Authors
- Ingook Jang, Hyunseok Kim, Seonghyun Kim
- Issue Date
- 2022-11
- Citation
- International Conference on Control, Automation and Systems (ICCAS) 2022, pp.1-2
- Publisher
- IEEE
- Language
- English
- Type
- Conference Paper
- Abstract
- Recently, it is a challenging issue that solves the robot manipulation problem with reinforcement learning. In this paper, we address an experimental study on applying multi-agent reinforcement learning to a multi-robot manipulation task. We design a collaborative robot manipulation task that can be solved only when two robot arms collaborate for a common goal. The experimental results demonstrate that the state-of-the-art method achieves good performance in terms of the cumulative reward and the success rate.
- KSP Keywords
- An experimental study, Collaborative robot, Multi-Robot, Reinforcement learning(RL), Robot manipulation, Success rate, multi-agent reinforcement learning, state-of-The-Art