Multiple-step greedy policies in online and approximate reinforcement learning - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2018

Multiple-step greedy policies in online and approximate reinforcement learning

Abstract

Multiple-step lookahead policies have demonstrated high empirical competence in Reinforcement Learning, via the use of Monte Carlo Tree Search or Model Predictive Control. In a recent work [5], multiple-step greedy policies and their use in vanilla Policy Iteration algorithms were proposed and analyzed. In this work, we study multiple-step greedy algorithms in more practical setups. We begin by highlighting a counter-intuitive difficulty, arising with soft-policy updates: even in the absence of approximations, and contrary to the 1-step-greedy case, monotonic policy improvement is not guaranteed unless the update stepsize is sufficiently large. Taking particular care about this difficulty, we formulate and analyze online and approximate algorithms that use such a multi-step greedy operator.
Fichier principal
Vignette du fichier
approximate_online_cr_final.pdf (343.92 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01927962 , version 1 (20-11-2018)

Identifiers

Cite

Yonathan Efroni, Gal Dalal, Bruno Scherrer, Shie Mannor. Multiple-step greedy policies in online and approximate reinforcement learning. NeurIPS 2018 - Thirty-second Conference on Neural Information Processing Systems, Dec 2018, Montréal, Canada. ⟨hal-01927962⟩
76 View
117 Download

Altmetric

Share

Gmail Facebook X LinkedIn More