Applying Deep Q-learning for Multi-agent Cooperative-Competitive Environments.

Anikó Kopacz Lehel Csató Camelia Chira

Published in: SOCO (2022)

Keyphrases

reinforcement learning
cooperative
highly dynamic
multi agent
state space
real world
learning algorithm
function approximation
dynamic programming
dynamic environments
optimal policy
complex environments
reinforcement learning algorithms
neural network
decision making
model free