Multitask Soft Option Learning
Maximilian Igl (University of Oxford)
Andrew Gambardella (University of Oxford)
J. He (TU Delft - Interactive Intelligence)
Nantas Nardelli (University of Oxford)
N Siddharth (University of Oxford)
Wendelin Böhmer (University of Oxford)
Shimon Whiteson (University of Oxford)
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
Abstract
We present Multitask Soft Option Learning (MSOL), a hierarchical multitask framework based on Planning as Inference. MSOL extends the concept of options, using separate variational posteriors for each task, regularized by a shared prior. This “soft” version of options avoids several instabilities during training in a multitask setting, and provides a natural way to learn both intra-option policies and their terminations. Furthermore, it allows fine-tuning of options for new tasks without forgetting their learned policies, leading to faster training without reducing the expressiveness of the hierarchical policy. We demonstrate empirically that MSOL significantly outperforms both hierarchical and flat transfer-learning baselines.