Disturbance Observable Reinforcement Learning that Compensates for Changes in Environment.

Seong-In Kim Takeshi Shibuya

Published in: SICE (2022)

Keyphrases

reinforcement learning
mobile robot
real robot
neural network
learning algorithm
dynamic environments
optimal policy
function approximation
real time
genetic algorithm
state space
computing environments
complex environments
environmental conditions
reinforcement learning algorithms
exploration strategy