Characterization of continuum robot arms under reinforcement learning and derived improvements.
Ryota MorimotoMasahiro IkedaRyuma NiiyamaYasuo KuniyoshiPublished in: Future Internet (2022)
Keyphrases
- reinforcement learning
- mobile robot
- robot control
- real robot
- human robot interaction
- vision system
- function approximation
- autonomous learning
- goal directed
- state space
- robot navigation
- multi robot
- autonomous robots
- dynamic programming
- model free
- perceptual aliasing
- simulated robot
- human robot
- mobile robotics
- position and orientation
- optimal policy
- multi agent
- temporal difference
- learning algorithm
- robotic systems
- multi armed bandits