Three-link planar arm control using reinforcement learning.
Wonchul KimTaewan KimH. Jin KimSungwan KimPublished in: URAI (2017)
Keyphrases
- reinforcement learning
- control problems
- optimal control
- real time
- robotic arm
- control policy
- robot control
- control system
- function approximation
- control strategies
- image sequences
- state space
- control theory
- optimal policy
- markov decision processes
- policy search
- model free
- d objects
- mobile robot
- multi agent
- machine learning