State-free Reinforcement Learning

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 \({S}^\Pi := \{ s|\max_{\pi\in \Pi}q^{P, \pi}(s)>0 \}\), we design an algorithm which requir...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2024-09
Main Authors: Chen, Mingyu, Pacchiano, Aldo, Zhang, Xuezhou
Format: Article
Language:English
Subjects:
Algorithms
Parameters
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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 \({S}^\Pi := \{ s|\max_{\pi\in \Pi}q^{P, \pi}(s)>0 \}\), 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 \({S}^\Pi\). 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.
ISSN:2331-8422