Stabilizing Visual Reinforcement Learning via Asymmetric Interactive Cooperation.
Yunpeng ZhaiPeixi PengYifan ZhaoYangru HuangYonghong TianPublished in: ICCV (2023)
Keyphrases
- reinforcement learning
- cooperative
- multi agent
- function approximation
- visual programming
- interactive visual
- visual interfaces
- visual representations
- model free
- multi agent systems
- dynamic programming
- computer graphics
- markov decision processes
- genetic algorithm
- information exchange
- low level
- visual perception
- visual exploration
- learning algorithm
- robotic control
- computer vision
- transition model
- visual data mining
- learning process
- visual analysis
- nonlinear systems
- visual data
- optimal control
- information sharing
- virtual reality
- user interaction
- supervised learning