A TD3-based multi-agent deep reinforcement learning method in mixed cooperation-competition environment.

Fengjiao Zhang Jie Li Zhi Li

Published in: Neurocomputing (2020)

Keyphrases

reinforcement learning
multi agent
high precision
model free
cost function
computational cost
preprocessing
mobile robot
experimental evaluation
neural network
significant improvement
cooperative
dynamic programming
state space
high accuracy
synthetic data
optimal policy
machine learning
data sets