Hierarchical average-reward linearly-solvable Markov decision processes

We introduce a novel approach to hierarchical reinforcement learning for Linearly-solvable Markov Decision Processes (LMDPs) in the infinite-horizon average-reward setting. Unlike previous work, our approach allows learning low-level and high-level tasks simultaneously, without imposing limiting res...

Descripción completa

Detalles Bibliográficos
Autores: Infante Molina, A. Guillermo, Jonsson, Anders, 1973-, Gómez Cerdà, Vicenç
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2024
País:España
Institución:Varias* (Consorci de Biblioteques Universitáries de Catalunya, Centre de Serveis Científics i Acadèmics de Catalunya)
Repositorio:Recercat. Dipósit de la Recerca de Catalunya
OAI Identifier:oai:dnet:recercat____::a26891e78aa4131fe29bf8cf46e5ee67
Acceso en línea:https://hdl.handle.net/10230/72913
http://dx.doi.org/10.3233/FAIA240631
Access Level:acceso abierto
Palabra clave:Markov, Processos de
Jerarquies
Anàlisi de tasques
Descripción
Sumario:We introduce a novel approach to hierarchical reinforcement learning for Linearly-solvable Markov Decision Processes (LMDPs) in the infinite-horizon average-reward setting. Unlike previous work, our approach allows learning low-level and high-level tasks simultaneously, without imposing limiting restrictions on the low-level tasks. Our method relies on partitions of the state space that create smaller subtasks that are easier to solve, and the equivalence between such partitions to learn more efficiently. We then exploit the compositionality of low-level tasks to exactly represent the value function of the high-level task. Experiments show that our approach can outperform flat average-reward reinforcement learning by one or several orders of magnitude.