Login / Signup
TERL: Two-Stage Ensemble Reinforcement Learning Paradigm for Large-Scale Decentralized Decision Making in Transportation Simulation.
Ziyuan Gu
Xun Yang
Qi Zhang
Wenwu Yu
Zhiyuan Liu
Published in:
IEEE Trans. Knowl. Data Eng. (2023)
Keyphrases
</>
reinforcement learning
decentralized decision making
optimal policy
neural network
function approximation
machine learning
multi agent
real robot
learning algorithm
ensemble learning
online learning
resource allocation
ensemble methods
robocup soccer