Print Email Facebook Twitter BADDr Title BADDr: Bayes-Adaptive Deep Dropout RL for POMDPs Author Katt, Sammie (Northeastern University) Nguyen, Hai (Northeastern University) Oliehoek, F.A. (TU Delft Interactive Intelligence) Amato, Christopher (Northeastern University) Date 2022 Abstract While reinforcement learning (RL) has made great advances in scalability, exploration and partial observability are still active research topics. In contrast, Bayesian RL (BRL) provides a principled answer to both state estimation and the exploration-exploitation trade-off, but struggles to scale. To tackle this challenge, BRL frameworks with various prior assumptions have been proposed, with varied success. This work presents a representation-agnostic formulation of BRL under partially observability, unifying the previous models under one theoretical umbrella. To demonstrate its practical significance we also propose a novel derivation, Bayes-Adaptive Deep Dropout rl (BADDr), based on dropout networks. Under this parameterization, in contrast to previous work, the belief over the state and dynamics is a more scalable inference problem. We choose actions through Monte-Carlo tree search and empirically show that our method is competitive with state-of-the-art BRL methods on small domains while being able to solve much larger ones. Subject Bayesian RLMCTSPOMDP To reference this document use: http://resolver.tudelft.nl/uuid:4f6dd8eb-f5a9-4fac-b21c-6639cf98b3eb 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, 2 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 Sammie Katt, Hai Nguyen, F.A. Oliehoek, Christopher Amato Files PDF 3535850.3535932.pdf 2.09 MB Close viewer /islandora/object/uuid:4f6dd8eb-f5a9-4fac-b21c-6639cf98b3eb/datastream/OBJ/view