Extending World Models for Multi-Agent Reinforcement Learning in MALMÖ

Valliappa Chockalingam, Tegg Tae Kyong Sung, Feryal Behbahani, Rishab Gargeya, Amlesh Sivanantham, Aleksandra Malysheva
2018 Artificial Intelligence and Interactive Digital Entertainment Conference  
Recent work in (deep) reinforcement learning has increasingly looked to develop better agents for multi-agent/multitask scenarios as many successes have already been seen in the usual single-task single-agent setting. In this paper, we propose a solution for a recently released benchmark which tests agents in such scenarios, namely the MARLÖ competition. Following the 2018 Jeju Deep Learning Camp, we consider a combined approach based on various ideas generated during the camp as well as
more » ... ions for building agents from recent research trends, similar to the methodology taken in developing Rainbow (Hessel et al. 2017 ). These choices include the following: using model-based agents which allows for planning/simulation and reduces computation costs when learning controllers, applying distributional reinforcement learning to reduce losses incurred from using mean estimators, considering curriculum learning for task selection when tasks differ in difficulty, and graph neural networks as an approach to communicate between agents. In this paper, we motivate each of these approaches and discuss a combined approach that we believe will fare well in the competition.
dblp:conf/aiide/ChockalingamSBG18 fatcat:g63hnabnwzejtjw4lxms5dwhc4