Pure Exploration Beyond Reward Feedback: The Role of Post-Action Context

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Shahverdikondori, Mohammad, Abouei, Amir Mohammad, Rezaeimoghadam, Alireza, Kiyavash, Negar
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916002001846272
author Shahverdikondori, Mohammad
Abouei, Amir Mohammad
Rezaeimoghadam, Alireza
Kiyavash, Negar
author_facet Shahverdikondori, Mohammad
Abouei, Amir Mohammad
Rezaeimoghadam, Alireza
Kiyavash, Negar
contents We introduce the problem of best arm identification (BAI) with post-action context, a new BAI problem in a stochastic multi-armed bandit environment and the fixed-confidence setting. The problem addresses the scenarios in which the learner receives a post-action context in addition to the reward after playing each action. This post-action context provides additional information that can significantly facilitate the decision process. We analyze two different types of the post-action context: (i) separator, where the reward depends solely on the context, and (ii) non-separator, where the reward depends on both the action and the context. For both cases, we derive instance-dependent lower bounds on the sample complexity and propose algorithms that asymptotically achieve the optimal sample complexity. For the separator setting, we propose a novel sampling rule called G-tracking, which uses the geometry of the context space to directly track the contexts rather than the actions. For the non-separator setting, we do so by demonstrating that the Track-and-Stop algorithm can be extended to this setting. Moreover, in both settings, we theoretically and empirically show that algorithms that ignore the post-action context are sub-optimal. Finally, our empirical results showcase the advantage of our approaches compared to the state of the art.
format Preprint
id arxiv_https___arxiv_org_abs_2502_03061
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Pure Exploration Beyond Reward Feedback: The Role of Post-Action Context
Shahverdikondori, Mohammad
Abouei, Amir Mohammad
Rezaeimoghadam, Alireza
Kiyavash, Negar
Machine Learning
We introduce the problem of best arm identification (BAI) with post-action context, a new BAI problem in a stochastic multi-armed bandit environment and the fixed-confidence setting. The problem addresses the scenarios in which the learner receives a post-action context in addition to the reward after playing each action. This post-action context provides additional information that can significantly facilitate the decision process. We analyze two different types of the post-action context: (i) separator, where the reward depends solely on the context, and (ii) non-separator, where the reward depends on both the action and the context. For both cases, we derive instance-dependent lower bounds on the sample complexity and propose algorithms that asymptotically achieve the optimal sample complexity. For the separator setting, we propose a novel sampling rule called G-tracking, which uses the geometry of the context space to directly track the contexts rather than the actions. For the non-separator setting, we do so by demonstrating that the Track-and-Stop algorithm can be extended to this setting. Moreover, in both settings, we theoretically and empirically show that algorithms that ignore the post-action context are sub-optimal. Finally, our empirical results showcase the advantage of our approaches compared to the state of the art.
title Pure Exploration Beyond Reward Feedback: The Role of Post-Action Context
topic Machine Learning
url https://arxiv.org/abs/2502.03061