Saved in:
Bibliographic Details
Main Author: Pastukhov, Sergey
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.04366
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • We introduce a novel hierarchical reinforcement learning (HRL) framework that performs top-down recursive planning via learned subgoals, successfully applied to the complex combinatorial puzzle game Sokoban. Our approach constructs a six-level policy hierarchy, where each higher-level policy generates subgoals for the level below. All subgoals and policies are learned end-to-end from scratch, without any domain knowledge. Our results show that the agent can generate long action sequences from a single high-level call. While prior work has explored 2-3 level hierarchies and subgoal-based planning heuristics, we demonstrate that deep recursive goal decomposition can emerge purely from learning, and that such hierarchies can scale effectively to hard puzzle domains.