Print Email Facebook Twitter Speeding up Deep Reinforcement Learning through Influence-Augmented Local Simulators Title Speeding up Deep Reinforcement Learning through Influence-Augmented Local Simulators Author Suau, M. (TU Delft Interactive Intelligence) He, J. (TU Delft Interactive Intelligence) Spaan, M.T.J. (TU Delft Algorithmics) Oliehoek, F.A. (TU Delft Interactive Intelligence) Date 2022 Abstract Learning effective policies for real-world problems is still an open challenge for the field of reinforcement learning (RL). The main limitation being the amount of data needed and the pace at which that data can be obtained. In this paper, we study how to build lightweight simulators of complicated systems that can run sufficiently fast for deep RL to be applicable. We focus on domains where agents interact with a reduced portion of a larger environment while still being affected by the global dynamics. Our method combines the use of local simulators with learned models that mimic the influence of the global system. The experiments reveal that incorporating this idea into the deep RL workflow can considerably accelerate the training process and presents several opportunities for the future. Subject Deep Reinforcement LearningInfluenceSimulation To reference this document use: http://resolver.tudelft.nl/uuid:0307bd82-46f0-4387-a805-53bf44c572b0 Publisher International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS) Embargo date 2022-12-05 ISBN 978-171385433-3 Source International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2022 Event 21st International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2022, 2022-05-09 → 2022-05-13, Auckland, Virtual, New Zealand Series Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS, 1548-8403, 3 Bibliographical note Green Open Access added to TU Delft Institutional Repository ‘You share, we take care!’ – Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public. Part of collection Institutional Repository Document type conference paper Rights © 2022 M. Suau, J. He, M.T.J. Spaan, F.A. Oliehoek Files PDF 3535850.3536093.pdf 1.44 MB Close viewer /islandora/object/uuid:0307bd82-46f0-4387-a805-53bf44c572b0/datastream/OBJ/view