paper-with-me

Papers

Stochastic Online Learning with Probabilistic Graph Feedback

2019-03-04 · Shuai Li, Wei Chen, Zheng Wen, Kwong-Sak Leung

We consider a problem of stochastic online learning with general probabilistic graph feedback, where each directed edge in the feedback graph has probability $p_{ij}$. Two cases are covered. (a) The one-step case, where after playing arm $i$ the learner observes a sample reward feedback of arm $j$ with independent probability $p_{ij}$. (b) The cascade case where after playing arm $i$ the learner observes feedback of all arms $j$ in a probabilistic cascade starting from $i$ -- for each $(i,j)$ with probability $p_{ij}$, if arm $i$ is played or observed, then a reward sample of arm $j$ would be observed with independent probability $p_{ij}$. Previous works mainly focus on deterministic graphs which corresponds to one-step case with $p_{ij} \in \{0,1\}$, an adversarial sequence of graphs with certain topology guarantees, or a specific type of random graphs. We analyze the asymptotic lower bounds and design algorithms in both cases. The regret upper bounds of the algorithms match the lower bounds with high probability.

📄 PDF Abstract BibTeX arXiv:1903.01083

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Stochastic MPC with Online-optimized Policies and Closed-loop Guarantees

2025-02-10 · Marcell Bartos, Alexandre Didier, Jerome Sieber, Johannes Köhler 외

This paper proposes a stochastic model predictive control method for linear systems affected by additive Gaussian disturbances. Closed-loop satisfaction of probabilistic constraints and recursive feasibility of the under…

Model Predictive Control

Online Learning with Dependent Stochastic Feedback Graphs

2020-01-01 · ICML 2020 1 · Corinna Cortes, Giulia Desalvo, Claudio Gentile, Mehryar Mohri 외

A general framework for online learning with partial information is one where feedback graphs specify which losses can be observed by the learner. We study a challenging scenario where feedback graphs vary stochastically…

Online Learning with Feedback Graphs Without the Graphs

2016-05-23 · Alon Cohen, Tamir Hazan, Tomer Koren

We study an online learning framework introduced by Mannor and Shamir (2011) in which the feedback is specified by a graph, in a setting where the graph may vary from round to round and is \emph{never fully revealed} to …

A Near-Optimal Best-of-Both-Worlds Algorithm for Online Learning with Feedback Graphs

2022-06-01 · Chloé Rouyer, Dirk van der Hoeven, Nicolò Cesa-Bianchi, Yevgeny Seldin

We consider online learning with feedback graphs, a sequential decision-making framework where the learner's feedback is determined by a directed graph over the action set. We present a computationally efficient algorith…

Decision MakingSequential Decision Making

Fast Stochastic MPC using Affine Disturbance Feedback Gains Learned Offline

2024-11-21 · Hotae Lee, Francesco Borrelli

We propose a novel Stochastic Model Predictive Control (MPC) for uncertain linear systems subject to probabilistic constraints. The proposed approach leverages offline learning to extract key features of affine disturban…

Computational EfficiencyModel Predictive Control