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.
@article{arxiv.1904.01033,
title = {Multitask Soft Option Learning},
author = {Maximilian Igl and Andrew Gambardella and Jinke He and Nantas Nardelli and N. Siddharth and Wendelin Böhmer and Shimon Whiteson},
journal= {arXiv preprint arXiv:1904.01033},
year = {2020}
}