Skip to Main content Skip to Navigation
Conference papers

Open Loop Execution of Tree-Search Algorithms

Abstract : In the context of tree-search stochastic planning algorithms where a generative model is available, we consider on-line planning algorithms building trees in order to recommend an action. We investigate the question of avoiding re-planning in subsequent decision steps by directly using sub-trees as action recommender. Firstly, we propose a method for open loop control via a new algorithm taking the decision of re-planning or not at each time step based on an analysis of the statistics of the sub-tree. Secondly, we show that the probability of selecting a suboptimal action at any depth of the tree can be upper bounded and converges towards zero. Moreover, this upper bound decays in a logarithmic way between subsequent depths. This leads to a distinction between node-wise optimality and state-wise optimality. Finally, we empirically demonstrate that our method achieves a compromise between loss of performance and computational gain.
Complete list of metadatas

Cited literature [3 references]  Display  Hide  Download
Contributor : Open Archive Toulouse Archive Ouverte (oatao) <>
Submitted on : Tuesday, October 23, 2018 - 4:52:55 PM
Last modification on : Friday, December 13, 2019 - 4:38:00 PM
Document(s) archivé(s) le : Thursday, January 24, 2019 - 4:42:41 PM


Files produced by the author(s)


  • HAL Id : hal-01902685, version 1
  • OATAO : 19924



Erwan Lecarpentier, Guillaume Infantes, Charles Lesire, Emmanuel Rachelson. Open Loop Execution of Tree-Search Algorithms. 2018 International Joint Conference on Artificial Intelligence (IJCAI 2018), Jul 2018, Stockholm, Sweden. pp.2362-2368. ⟨hal-01902685⟩



Record views


Files downloads