Reinforcement Learning for Vision-based Object Manipulation with Non-parametric Policy and Action Primitives.
Dongwon SonMyungsin KimJaecheol SimWonsik ShinPublished in: CoRR (2022)
Keyphrases
- object manipulation
- reinforcement learning
- robot control
- optimal policy
- action primitives
- action recognition
- human activity recognition
- robotic systems
- markov decision processes
- function approximation
- control policy
- activity recognition
- state space
- human computer interaction
- autonomous robots
- dynamic programming
- manipulation tasks
- real time
- human activities
- mobile robot
- vision system
- learning algorithm
- model free
- computer vision