Towards Automata-Based Abstraction of Goals in Hierarchical Reinforcement Learning
Résumé
Hierarchical Reinforcement Learning (HRL) offers potential benefits for solving long horizon tasks, generally unhandled by standard Reinforcement Learning (RL) techniques, by decomposing the problem and combining simple policies to achieve the goal. They are however still held back by the curse of dimensionality and the ambiguity of selected subtasks. We explore relevant approaches in HRL while highlighting the key challenges of goal representation, high-level planning and propose a research outline tackling them.
| Origine | Fichiers produits par l'(les) auteur(s) |
|---|