State-free Reinforcement Learning

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Chen, Mingyu, Pacchiano, Aldo, Zhang, Xuezhou
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866910622792286208
author Chen, Mingyu
Pacchiano, Aldo
Zhang, Xuezhou
author_facet Chen, Mingyu
Pacchiano, Aldo
Zhang, Xuezhou
contents In this work, we study the \textit{state-free RL} problem, where the algorithm does not have the states information before interacting with the environment. Specifically, denote the reachable state set by ${S}^Π:= \{ s|\max_{π\in Π}q^{P, π}(s)>0 \}$, we design an algorithm which requires no information on the state space $S$ while having a regret that is completely independent of ${S}$ and only depend on ${S}^Π$. We view this as a concrete first step towards \textit{parameter-free RL}, with the goal of designing RL algorithms that require no hyper-parameter tuning.
format Preprint
id arxiv_https___arxiv_org_abs_2409_18439
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle State-free Reinforcement Learning
Chen, Mingyu
Pacchiano, Aldo
Zhang, Xuezhou
Machine Learning
Artificial Intelligence
In this work, we study the \textit{state-free RL} problem, where the algorithm does not have the states information before interacting with the environment. Specifically, denote the reachable state set by ${S}^Π:= \{ s|\max_{π\in Π}q^{P, π}(s)>0 \}$, we design an algorithm which requires no information on the state space $S$ while having a regret that is completely independent of ${S}$ and only depend on ${S}^Π$. We view this as a concrete first step towards \textit{parameter-free RL}, with the goal of designing RL algorithms that require no hyper-parameter tuning.
title State-free Reinforcement Learning
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2409.18439