Comparison of Deep Reinforcement Learning-Based Guidance Strategies under Non-Ideal Conditions.

Sevket Utku Aydinli Ali Türker Kutay

Published in: CoDIT (2023)

Keyphrases

reinforcement learning
sufficient conditions
multi agent
statistical analysis
neural network
machine learning
learning process
state space
markov decision processes
function approximation
selection strategies
learning agents
data mining
artificial intelligence
mobile robot