Grid geometry is a foundational but rarely examined design choice in Reinforcement Learning (RL) environments for spatial exploration. We introduce HexaWorld and SquareWorld, two structurally parallel RL environments differing exclusively in their underlying discretization, and present a controlled comparison of hexagonal versus square grids under partial observability and finite energy budgets. Both environments are instantiated over three Mediterranean regions using Copernicus Marine Service and EMODnet data, with composite stress indices operationalized as reward signals. Across 135 matched configurations trained with MaskablePPO, HexaWorld outperforms SquareWorld in 79% of cases, with the advantage scaling with energy budget and habitat depth. A per-biozone analysis reveals a depth-dependent dissociation: SquareWorld achieves higher exploration efficiency in shallow zones, while HexaWorld translates coverage into reward more effectively at circalittoral and bathyal depths, suggesting hexagonal discretization as the stronger choice for deep benthic stress monitoring.

HexaWorld: The Role of Grid Geometries in Constrained RL Exploration / Lombardi, G., Bianchi, L.A., Schneider, R.. - 16978:(2027), pp. 115-127. (12th IAPR TC3 Workshop on Artificial Neural Networks in Pattern Recognition, ANNPR 2025 ita 2026) [10.1007/978-3-032-39028-8_10].

HexaWorld: The Role of Grid Geometries in Constrained RL Exploration

Giulia Lombardi
;
Luigi Amedeo Bianchi;
2027-01-01

Abstract

Grid geometry is a foundational but rarely examined design choice in Reinforcement Learning (RL) environments for spatial exploration. We introduce HexaWorld and SquareWorld, two structurally parallel RL environments differing exclusively in their underlying discretization, and present a controlled comparison of hexagonal versus square grids under partial observability and finite energy budgets. Both environments are instantiated over three Mediterranean regions using Copernicus Marine Service and EMODnet data, with composite stress indices operationalized as reward signals. Across 135 matched configurations trained with MaskablePPO, HexaWorld outperforms SquareWorld in 79% of cases, with the advantage scaling with energy budget and habitat depth. A per-biozone analysis reveals a depth-dependent dissociation: SquareWorld achieves higher exploration efficiency in shallow zones, while HexaWorld translates coverage into reward more effectively at circalittoral and bathyal depths, suggesting hexagonal discretization as the stronger choice for deep benthic stress monitoring.
2027
Lecture Notes in Computer Science
Heidelberg
Springer Science and Business Media Deutschland GmbH
9783032390271
9783032390288
Lombardi, Giulia; Bianchi, Luigi Amedeo; Schneider, Rochelle
HexaWorld: The Role of Grid Geometries in Constrained RL Exploration / Lombardi, G., Bianchi, L.A., Schneider, R.. - 16978:(2027), pp. 115-127. (12th IAPR TC3 Workshop on Artificial Neural Networks in Pattern Recognition, ANNPR 2025 ita 2026) [10.1007/978-3-032-39028-8_10].
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11572/510676
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
  • OpenAlex ND
social impact