Policy Search with Rare Significant Events: Choosing the Right Partner to Cooperate with - Sorbonne Université Access content directly
Journal Articles PLoS ONE Year : 2022

Policy Search with Rare Significant Events: Choosing the Right Partner to Cooperate with

Abstract

This paper focuses on a class of reinforcement learning problems where significant events are rare and limited to a single positive reward per episode. A typical example is that of an agent who has to choose a partner to cooperate with, while a large number of partners are simply not interested in cooperating, regardless of what the agent has to offer. We address this problem in a continuous state and action space with two different kinds of search methods: a gradient policy search method and a direct policy search method using an evolution strategy. We show that when significant events are rare, gradient information is also scarce, making it difficult for policy gradient search methods to find an optimal policy, with or without a deep neural architecture. On the other hand, we show that direct policy search methods are invariant to the rarity of significant events, which is yet another confirmation of the unique role evolutionary algorithms has to play as a reinforcement learning method.
Fichier principal
Vignette du fichier
2021 - Policy search Arxiv 2103.06846.pdf (1.52 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03315730 , version 1 (05-08-2021)

Identifiers

Cite

Paul Ecoffet, Nicolas Fontbonne, Jean-Baptiste André, Nicolas Bredeche. Policy Search with Rare Significant Events: Choosing the Right Partner to Cooperate with. PLoS ONE, 2022, PLoS ONE, 17 (4), pp.e0266841. ⟨10.1371/journal.pone.0266841⟩. ⟨hal-03315730⟩
50 View
40 Download

Altmetric

Share

Gmail Facebook X LinkedIn More