Multi-objective Monte-Carlo Tree Search - Archive ouverte HAL Access content directly
Conference Papers Year : 2012

Multi-objective Monte-Carlo Tree Search

(1, 2) , (1, 2)


Concerned with multi-objective reinforcement learning (MORL), this paper presents MO-MCTS, an extension of Monte-Carlo Tree Search to multi-objective sequential decision making. The known multi-objective indicator referred to as hyper-volume indicator is used to define an action selection criterion, replacing the UCB criterion in order to deal with multi-dimensional rewards. MO-MCTS is firstly compared with an existing MORL algorithm on the artificial Deep Sea Treasure problem. Then a scalability study of MO-MCTS is made on the NP-hard problem of grid scheduling, showing that the performance of MO-MCTS matches the non RL-based state of the art albeit with a higher computational cost.
Fichier principal
Vignette du fichier
wang88.pdf (899.53 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-00758379 , version 1 (28-11-2012)


  • HAL Id : hal-00758379 , version 1


Weijia Wang, Michèle Sebag. Multi-objective Monte-Carlo Tree Search. Asian Conference on Machine Learning, Nov 2012, Singapour, Singapore. pp.507-522. ⟨hal-00758379⟩
448 View
766 Download


Gmail Facebook Twitter LinkedIn More