- TL;DR: In Hierarchical RL, we introduce the notion of a 'soft', i.e. adaptable, option and show that this helps learning in multitask settings.
- Abstract: We present Multitask Soft Option Learning (MSOL), a hierarchical multi-task framework based on Planning-as-Inference. MSOL extends the concept of Options, using separate variational posteriors for each task, regularized by a shared prior. The learned soft-options are temporally extended, allowing a higher-level master policy to train faster on new tasks by making decisions with lower frequency. Additionally, MSOL allows fine-tuning of soft-options for new tasks without unlearning previously useful behavior, and avoids problems with local minima in multitask training. We demonstrate empirically that MSOL significantly outperforms both hierarchical and flat transfer-learning baselines in challenging multi-task environments.
- Keywords: Hierarchical Reinforcement Learning, Reinforcement Learning, Control as Inference, Options, Multitask Learning
- Original Pdf: pdf