- document
-
Analysing factorizations of action-value networks for cooperative multi-agent reinforcement learningCastellini, Jacopo (author), Oliehoek, F.A. (author), Savani, Rahul (author), Whiteson, Shimon (author)Recent years have seen the application of deep reinforcement learning techniques to cooperative multi-agent systems, with great empirical success. However, given the lack of theoretical insight, it remains unclear what the employed neural networks are learning, or how we should enhance their learning power to address the problems on which...journal article 2021