Výsledky vyhledávání - "Infante, Guillermo"

Report

Hierarchical Average-Reward Linearly-solvable Markov Decision Processes

Autor: Infante, Guillermo, Jonsson, Anders, Gómez, Vicenç

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 t

Externí odkaz: http://arxiv.org/abs/2407.06690

Zobrazit plný text záznamu

Report

Planning with a Learned Policy Basis to Optimally Solve Complex Tasks

Autor: Infante, Guillermo, Kuric, David, Jonsson, Anders, Gómez, Vicenç, van Hoof, Herke

Conventional reinforcement learning (RL) methods can successfully solve a wide range of sequential decision problems. However, learning policies that can generalize predictably across multiple tasks in a setting with non-Markovian reward specificatio

Externí odkaz: http://arxiv.org/abs/2403.15301

Zobrazit plný text záznamu

Akademický článek

Phylogenomic insights into Neotropical Magnolia relationships

Autor: Aldaba Núñez, Fabián A., Guzmán-Díaz, Salvador, Veltjen, Emily, Asselman, Pieter, Esteban Jiménez, José, Valdés Sánchez, Jorge, Testé, Ernesto, Pino Infante, Guillermo, Silva Sierra, Daniel, Callejas Posada, Ricardo, Hernández Najarro, Francisco, Vázquez-García, J. Antonio, Larridon, Isabel, Park, Suhyeon, Kim, Sangtae, Martínez Salas, Esteban M., Samain, Marie-Stéphanie

Publikováno v: In Heliyon 30 October 2024 10(20)

Zobrazit plný text záznamu

Report

Globally Optimal Hierarchical Reinforcement Learning for Linearly-Solvable Markov Decision Processes

Autor: Infante, Guillermo, Jonsson, Anders, Gómez, Vicenç

Publikováno v: The Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI-22), 2022

In this work we present a novel approach to hierarchical reinforcement learning for linearly-solvable Markov decision processes. Our approach assumes that the state space is partitioned, and the subtasks consist in moving between the partitions. We r

Externí odkaz: http://arxiv.org/abs/2106.15380

Zobrazit plný text záznamu