@conference {Bhalla2019,
	title = {Training Cooperative Agents for Multi-Agent Reinforcement Learning},
	booktitle = {Proc. of the 18th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2019)},
	year = {2019},
	address = {Montreal, Canada},
	abstract = {Deep Learning and back-propagation has been successfully used to perform centralized training with communication protocols among multiple agents in a cooperative environment. In this paper we present techniques for centralized training of Multi-Agent (Deep) Reinforcement Learning (MARL) using the model-free Deep Q-Network as the baseline model and message sharing between agents. We present a novel, scalable, centralized MARL training technique, which separates the message learning module from the policy module. The separation of these modules helps in faster convergence in complex domains like autonomous driving simulators. A second contribution uses the centrally trained model to bootstrap training of distributed, independent, cooperative agent policies for execution and thus addresses the challenges of noise and communication bottlenecks in real-time communication channels. This paper theoretically and empirically compares our centralized training algorithms to current research in the field of MARL. We also present and release a new OpenAI-Gym environment which can be used for multi-agent research as it simulates multiple autonomous cars driving cooperatively on a highway.},
	keywords = {Autonomous Driving, MARL, Multi-Agent Reinforcement Learning, MultiAgent Systems, reinforcement learning},
	author = {Bhalla, Sushrut and Subramanian, Sriram Ganapathi and Crowley, Mark},
	editor = {Agmon, N. and Taylor, M.E. and Elkind, E. and Veloso, M.}
}