Robotic Knee Parameter Tuning Using Approximate Policy Iteration.

Xiang Gao Yue Wen Minhan Li Jennie Si He (Helen) Huang

Published in: ICCSIP (1) (2018)

Keyphrases

parameter tuning
approximate policy iteration
policy iteration
reinforcement learning
ink bleed
mobile robot
markov decision problems
parameter settings
policy search
robotic systems
temporal difference
markov decision processes
fixed point
genetic algorithm
learning algorithm
neural network
model free