Hierarchical reinforcement learning with natural language subgoals
Abstract
Hierarchical reinforcement learning has been a compelling approach for achieving goal directed behavior over long sequences of actions. However, it has been challenging to implement in realistic or open-ended environments. A main challenge has been to find the right space of sub-goals over which to instantiate a hierarchy. We present a novel approach where we use data from humans solving these tasks to softly supervise the goal space for a set of long range tasks in a 3D embodied environment. In particular, we use unconstrained natural language to parameterize this space. This has two advantages: first, it is easy to generate this data from naive human participants; second, it is flexible enough to represent a vast range of sub-goals in human-relevant tasks. Our approach outperforms agents that clone expert behavior on these tasks, as well as HRL from scratch without this supervised sub-goal space. Our work presents a novel approach to combining human expert supervision with the benefits and flexibility of reinforcement learning.
Keywords
Cite
@article{arxiv.2309.11564,
title = {Hierarchical reinforcement learning with natural language subgoals},
author = {Arun Ahuja and Kavya Kopparapu and Rob Fergus and Ishita Dasgupta},
journal= {arXiv preprint arXiv:2309.11564},
year = {2023}
}