Print Email Facebook Twitter Difference rewards policy gradients Title Difference rewards policy gradients Author Castellini, Jacopo (University of Liverpool) Devlin, Sam (Microsoft Research Cambridge) Oliehoek, F.A. (TU Delft Interactive Intelligence) Savani, Rahul (University of Liverpool) Date 2022 Abstract Policy gradient methods have become one of the most popular classes of algorithms for multi-agent reinforcement learning. A key challenge, however, that is not addressed by many of these methods is multi-agent credit assignment: assessing an agent’s contribution to the overall performance, which is crucial for learning good policies. We propose a novel algorithm called Dr.Reinforce that explicitly tackles this by combining difference rewards with policy gradients to allow for learning decentralized policies when the reward function is known. By differencing the reward function directly, Dr.Reinforce avoids difficulties associated with learning the Q-function as done by counterfactual multi-agent policy gradients (COMA), a state-of-the-art difference rewards method. For applications where the reward function is unknown, we show the effectiveness of a version of Dr.Reinforce that learns an additional reward network that is used to estimate the difference rewards. Subject Difference rewardsMulti-agent credit assignmentMulti-agent reinforcement learningPolicy gradientsReward learning To reference this document use: http://resolver.tudelft.nl/uuid:b47d136e-6080-4876-a299-43c68d7ff46e DOI https://doi.org/10.1007/s00521-022-07960-5 ISSN 0941-0643 Source Neural Computing and Applications Part of collection Institutional Repository Document type journal article Rights © 2022 Jacopo Castellini, Sam Devlin, F.A. Oliehoek, Rahul Savani Files PDF s00521_022_07960_5.pdf 16.04 MB Close viewer /islandora/object/uuid:b47d136e-6080-4876-a299-43c68d7ff46e/datastream/OBJ/view