Multifingered Grasping Based on Multimodal Reinforcement Learning.
Hongzhuo LiangLin CongNorman HendrichShuang LiFuchun SunJianwei ZhangPublished in: IEEE Robotics Autom. Lett. (2022)
Keyphrases
- reinforcement learning
- function approximation
- vision system
- multimodal interaction
- temporal difference
- machine learning
- reinforcement learning algorithms
- state space
- multi agent
- optimal policy
- audio visual
- model free
- active learning
- multi agent reinforcement learning
- markov decision processes
- robotic control
- brain image analysis
- motor skills
- policy search
- reinforcement learning methods
- action space
- markov decision process
- optimal control
- learning capabilities
- human robot interaction
- learning classifier systems
- real time
- multi modal
- supervised learning
- search space
- multimedia
- learning algorithm
- data sets