Coordinated reinforcement learningCoordinated reinforcement learning Πλήρης Δημοσίευση σε Συνέδριο Conference Full Paper 2015-11-132002enWe present several new algorithms for multiagent reinforcement learning. A common feature of these algorithms is a parameterized, structured representation of a policy or value function. This structure is leveraged in an approach we call coordinated reinforcement learning, by which agents coordinate both their action selection activities and their parameter updates. Within the limits of our parametric representations, the agents will determine a jointly optimal action without explicitly considering every possible action in their exponentially large joint action space. Our methods differ from many previous reinforcement learning approaches to multiagent coordination in that structured communication and coordination between agents appears at the core of both the learning algorithm and the execution architecture. Our experimental results, comparing our approach to other RL methods, illustrate both the quality of the policies obtained and the additional benefits of coordination. http://creativecommons.org/licenses/by/4.0/227–23419th International Conference on Machine LearningProceedings of the 19th International Conference on Machine Learning (ICML), Sydney, Australia, July 2002 Lagoudakis Michael Λαγουδακης Μιχαηλ Guestrin, C. Parr, R. Reinforcement Learning