Keywords: representation hierarchy reinforcement learning
TL;DR: We translate a bound on sub-optimality of representations to a practical training objective in the context of hierarchical reinforcement learning.
Abstract: We study the problem of representation learning in goal-conditioned hierarchical reinforcement learning. In such hierarchical structures, a higher-level controller solves tasks by iteratively communicating goals which a lower-level policy is trained to reach. Accordingly, the choice of representation -- the mapping of observation space to goal space -- is crucial. To study this problem, we develop a notion of sub-optimality of a representation, defined in terms of expected reward of the optimal hierarchical policy using this representation. We derive expressions which bound the sub-optimality and show how these expressions can be translated to representation learning objectives which may be optimized in practice. Results on a number of difficult continuous-control tasks show that our approach to representation learning yields qualitatively better representations as well as quantitatively better hierarchical policies, compared to existing methods.
Code: [![github](/images/github_icon.svg) tensorflow/models](https://github.com/tensorflow/models) + [![Papers with Code](/images/pwc_icon.svg) 6 community implementations](https://paperswithcode.com/paper/?openreview=H1emus0qF7)