Cell-Free Latent Go-Explore - Archive ouverte HAL Access content directly
Conference Papers Year : 2023

Cell-Free Latent Go-Explore

Abstract

In this paper, we introduce Latent Go-Explore (LGE), a simple and general approach based on the Go-Explore paradigm for exploration in reinforcement learning (RL). Go-Explore was initially introduced with a strong domain knowledge constraint for partitioning the state space into cells. However, in most real-world scenarios, drawing domain knowledge from raw observations is complex and tedious. If the cell partitioning is not informative enough, Go-Explore can completely fail to explore the environment. We argue that the Go-Explore approach can be generalized to any environment without domain knowledge and without cells by exploiting a learned latent representation. Thus, we show that LGE can be flexibly combined with any strategy for learning a latent representation. We show that LGE, although simpler than Go-Explore, is more robust and outperforms all state-of-the-art algorithms in terms of pure exploration on multiple hard-exploration environments. The LGE implementation is available as open-source at https://github.com/qgallouedec/lge.
Fichier principal
Vignette du fichier
gallouedec23a.pdf (1.51 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03769875 , version 1 (18-12-2023)

Identifiers

Cite

Quentin Gallouédec, Emmanuel Dellandréa. Cell-Free Latent Go-Explore. International Conference on Machine Learning (ICML), Jul 2023, Honolulu (Hawai), United States. ⟨hal-03769875⟩
60 View
21 Download

Altmetric

Share

Gmail Facebook X LinkedIn More