Goal Space Abstraction in Hierarchical Reinforcement Learning via Reachability Analysis - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2023

Goal Space Abstraction in Hierarchical Reinforcement Learning via Reachability Analysis

Abstract

Open-ended learning benefits immensely from the use of symbolic methods for goal representation as they offer ways to structure knowledge for efficient and transferable learning. However, the existing Hierarchical Reinforcement Learning (HRL) approaches relying on symbolic reasoning are often limited as they require a manual goal representation. The challenge in autonomously discovering a symbolic goal representation is that it must preserve critical information, such as the environment dynamics. In this work, we propose a developmental mechanism for subgoal discovery via an emergent representation that abstracts (i.e., groups together) sets of environment states that have similar roles in the task. We create a HRL algorithm that gradually learns this representation along with the policies and evaluate it on navigation tasks to show the learned representation is interpretable and results in data efficiency.
Fichier principal
Vignette du fichier
ZademImol2023.pdf (587.71 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-04201363 , version 1 (11-09-2023)

Licence

Attribution

Identifiers

Cite

Mehdi Zadem, Sergio Mover, Sao Mai Nguyen. Goal Space Abstraction in Hierarchical Reinforcement Learning via Reachability Analysis. IMOL 2023 - The 6th International Workshop on Intrinsically Motivated Open-ended Learning, Sep 2023, Paris, France. ⟨hal-04201363⟩
43 View
28 Download

Altmetric

Share

Gmail Facebook X LinkedIn More