Cover Image

Adapting to Stochastic and Adversarial Losses in Episodic MDPs with Aggregate Bandit Feedback

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ito, Shinji, Jamieson, Kevin, Luo, Haipeng, Maiti, Arnab, Tsuchiya, Taira
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Reinforcement Learning from Adversarial Preferences in Tabular MDPs
by: Tsuchiya, Taira, et al.
Published: (2025)

Adversarial Learning in Games with Bandit Feedback: Logarithmic Pure-Strategy Maximin Regret
by: Ito, Shinji, et al.
Published: (2026)

Instance-Dependent Regret Bounds for Learning Two-Player Zero-Sum Games with Bandit Feedback
by: Ito, Shinji, et al.
Published: (2025)

Scale-Invariant Fast Convergence in Games
by: Tsuchiya, Taira, et al.
Published: (2026)

Corrupted Learning Dynamics in Games
by: Tsuchiya, Taira, et al.
Published: (2024)

Fast Rates in Stochastic Online Convex Optimization by Exploiting the Curvature of Feasible Sets
by: Tsuchiya, Taira, et al.
Published: (2024)

Near-Optimal Regret in Linear MDPs with Aggregate Bandit Feedback
by: Cassel, Asaf, et al.
Published: (2024)

On the Power of Adaptivity for $\varepsilon$-Best Arm Identification in Linear Bandits
by: Maiti, Arnab, et al.
Published: (2026)

Exploration by Optimization with Hybrid Regularizers: Logarithmic Regret with Adversarial Robustness in Partial Monitoring
by: Tsuchiya, Taira, et al.
Published: (2024)

A Simple and Adaptive Learning Rate for FTRL in Online Learning with Minimax Regret of $Θ(T^{2/3})$ and its Application to Best-of-Both-Worlds
by: Tsuchiya, Taira, et al.
Published: (2024)

Efficient Near-Optimal Algorithm for Online Shortest Paths in Directed Acyclic Graphs with Bandit Feedback Against Adaptive Adversaries
by: Maiti, Arnab, et al.
Published: (2025)

Stability-penalty-adaptive follow-the-regularized-leader: Sparsity, game-dependency, and best-of-both-worlds
by: Tsuchiya, Taira, et al.
Published: (2023)

Adaptive Learning Rate for Follow-the-Regularized-Leader: Competitive Analysis and Best-of-Both-Worlds
by: Ito, Shinji, et al.
Published: (2024)

On the Limitations and Possibilities of Nash Regret Minimization in Zero-Sum Matrix Games under Noisy Feedback
by: Maiti, Arnab, et al.
Published: (2023)

Bandit and Delayed Feedback in Online Structured Prediction
by: Shibukawa, Yuki, et al.
Published: (2025)

Data- and Variance-dependent Regret Bounds for Online Tabular MDPs
by: Li, Mingyi, et al.
Published: (2026)

Beating Adversarial Low-Rank MDPs with Unknown Transition and Bandit Feedback
by: Liu, Haolin, et al.
Published: (2024)

Nearly Minimax Optimal Submodular Maximization with Bandit Feedback
by: Tajdini, Artin, et al.
Published: (2023)

Improved Algorithm for Adversarial Linear Mixture MDPs with Bandit Feedback and Unknown Transition
by: Li, Long-Fei, et al.
Published: (2024)

Near-optimal Regret Using Policy Optimization in Online MDPs with Aggregate Bandit Feedback
by: Lancewicki, Tal, et al.
Published: (2025)

Heavy-tailed Linear Bandits: Adversarial Robustness, Best-of-both-worlds, and Beyond
by: Zhao, Canzhe, et al.
Published: (2025)

Learning to Incentivize in Repeated Principal-Agent Problems with Adversarial Agent Arrivals
by: Liu, Junyan, et al.
Published: (2025)

Learning Kernel-Based MDPs from Episodic Preferential Feedback
by: Pavlovic, Nikola, et al.
Published: (2026)

Near-Optimal Regret in Adversarial Kernel Bandits
by: Zhang, Yu-Jie, et al.
Published: (2026)

Online Control of Linear Systems under Unbounded Noise
by: Ito, Kaito, et al.
Published: (2024)

Efficient Uncoupled Learning Dynamics with $\tilde{O}\!\left(T^{-1/4}\right)$ Last-Iterate Convergence in Bilinear Saddle-Point Problems over Convex Sets under Bandit Feedback
by: Maiti, Arnab, et al.
Published: (2026)

Efficient Contextual Bandits with Uninformed Feedback Graphs
by: Zhang, Mengxiao, et al.
Published: (2024)

Slowly Changing Adversarial Bandit Algorithms are Efficient for Discounted MDPs
by: Kash, Ian A., et al.
Published: (2022)

Learning Adversarial MDPs with Stochastic Hard Constraints
by: Stradi, Francesco Emanuele, et al.
Published: (2024)

LC-Tsallis-INF: Generalized Best-of-Both-Worlds Linear Contextual Bandits
by: Kato, Masahiro, et al.
Published: (2024)

Influential Bandits: Pulling an Arm May Change the Environment
by: Sato, Ryoma, et al.
Published: (2025)

Bandit Max-Min Fair Allocation
by: Harada, Tsubasa, et al.
Published: (2025)

Follow-the-Perturbed-Leader with Fréchet-type Tail Distributions: Optimality in Adversarial Bandits and Best-of-Both-Worlds
by: Lee, Jongyeong, et al.
Published: (2024)

Online Learning in MDPs with Partially Adversarial Transitions and Losses
by: Schlisselberg, Ofir, et al.
Published: (2026)

Online Structured Prediction with Fenchel--Young Losses and Improved Surrogate Regret for Online Multiclass Classification with Logistic Loss
by: Sakaue, Shinsaku, et al.
Published: (2024)

Bandits with Stochastic Experts: Constant Regret, Empirical Experts and Episodes
by: Sharma, Nihal, et al.
Published: (2021)

Revisiting Online Learning Approach to Inverse Linear Optimization: A Fenchel$-$Young Loss Perspective and Gap-Dependent Regret Analysis
by: Sakaue, Shinsaku, et al.
Published: (2025)

Near-Optimal Last-Iterate Convergence for Zero-Sum Games with Bandit Feedback and Opponent Actions
by: Hait, Soumita, et al.
Published: (2026)

Best-of-Both-Worlds Algorithms for Linear Contextual Bandits
by: Kuroki, Yuko, et al.
Published: (2023)

An Axiomatic Approach to Loss Aggregation and an Adapted Aggregating Algorithm
by: Pacheco, Armando J. Cabrera, et al.
Published: (2024)