English
Related papers

Related papers: Efficient Rate Optimal Regret for Adversarial Cont…

200 papers

We consider the recently proposed reinforcement learning (RL) framework of Contextual Markov Decision Processes (CMDP), where the agent interacts with a (potentially adversarial) sequence of episodic tabular MDPs. In addition, a context…

Machine Learning · Computer Science 2020-06-19 Aditya Modi , Ambuj Tewari

We consider online learning for episodic stochastically constrained Markov decision processes (CMDPs), which plays a central role in ensuring the safety of reinforcement learning. Here the loss function can vary arbitrarily across the…

Machine Learning · Computer Science 2021-10-19 Shuang Qiu , Xiaohan Wei , Zhuoran Yang , Jieping Ye , Zhaoran Wang

Learning from human feedback plays an important role in aligning generative models, such as large language models (LLM). However, the effectiveness of this approach can be influenced by adversaries, who may intentionally provide misleading…

Machine Learning · Computer Science 2025-11-13 Qiwei Di , Jiafan He , Quanquan Gu

We study episodic linear mixture MDPs with the unknown transition and adversarial rewards under full-information feedback, employing dynamic regret as the performance measure. We start with in-depth analyses of the strengths and limitations…

Machine Learning · Computer Science 2024-11-06 Long-Fei Li , Peng Zhao , Zhi-Hua Zhou

We study the problem of reinforcement learning in infinite-horizon discounted linear Markov decision processes (MDPs), and propose the first computationally efficient algorithm achieving rate-optimal regret guarantees in this setting. Our…

Machine Learning · Computer Science 2026-03-16 Antoine Moulin , Gergely Neu , Luca Viano

A recent goal in the Reinforcement Learning (RL) framework is to choose a sequence of actions or a policy to maximize the reward collected or minimize the regret incurred in a finite time horizon. For several RL problems in operation…

Machine Learning · Computer Science 2016-08-18 K J Prabuchandran , Tejas Bodas , Theja Tulabandhula

This paper considers the best policy identification (BPI) problem in online Constrained Markov Decision Processes (CMDPs). We are interested in algorithms that are model-free, have low regret, and identify an approximately optimal policy…

Machine Learning · Computer Science 2024-04-16 Zihan Zhou , Honghao Wei , Lei Ying

We present a new anytime algorithm that achieves near-optimal regret for any instance of finite stochastic partial monitoring. In particular, the new algorithm achieves the minimax regret, within logarithmic factors, for both "easy" and…

Machine Learning · Computer Science 2012-07-03 Gabor Bartok , Navid Zolghadr , Csaba Szepesvari

A new algorithm for regret minimization in online convex optimization is described. The regret of the algorithm after $T$ time periods is $O(\sqrt{T \log T})$ - which is the minimum possible up to a logarithmic term. In addition, the new…

Machine Learning · Computer Science 2023-07-24 Elad Hazan , Nimrod Megiddo

We revisit the problem of \textit{online linear optimization} in case the set of feasible actions is accessible through an approximated linear optimization oracle with a factor $\alpha$ multiplicative approximation guarantee. This setting…

Machine Learning · Computer Science 2017-09-12 Dan Garber

We consider the general (stochastic) contextual bandit problem under the realizability assumption, i.e., the expected reward, as a function of contexts and actions, belongs to a general function class $\mathcal{F}$. We design a fast and…

Machine Learning · Computer Science 2021-07-13 David Simchi-Levi , Yunzong Xu

We propose an algorithmic framework, Offline Estimation to Decisions (OE2D), that reduces contextual bandit learning with general reward function approximation to offline regression. The framework allows near-optimal regret for contextual…

Machine Learning · Computer Science 2026-02-11 Hao Qin , Chicheng Zhang

Counterfactual regret minimization (CFR) is a family of algorithms for effectively solving imperfect-information games. It decomposes the total regret into counterfactual regrets, utilizing local regret minimization algorithms, such as…

Machine Learning · Computer Science 2024-05-15 Hang Xu , Kai Li , Bingyun Liu , Haobo Fu , Qiang Fu , Junliang Xing , Jian Cheng

While quantum reinforcement learning (RL) has attracted a surge of attention recently, its theoretical understanding is limited. In particular, it remains elusive how to design provably efficient quantum RL algorithms that can address the…

Quantum Physics · Physics 2024-06-14 Han Zhong , Jiachen Hu , Yecheng Xue , Tongyang Li , Liwei Wang

In constrained Markov decision processes (CMDPs) with adversarial rewards and constraints, a well-known impossibility result prevents any algorithm from attaining both sublinear regret and sublinear constraint violation, when competing…

Machine Learning · Computer Science 2024-09-27 Francesco Emanuele Stradi , Anna Lunghi , Matteo Castiglioni , Alberto Marchesi , Nicola Gatti

We investigate online convex optimization in non-stationary environments and choose the dynamic regret as the performance measure, defined as the difference between cumulative loss incurred by the online algorithm and that of any feasible…

Machine Learning · Computer Science 2020-12-01 Peng Zhao , Yu-Jie Zhang , Lijun Zhang , Zhi-Hua Zhou

The Adversarial Markov Decision Process (AMDP) is a learning framework that deals with unknown and varying tasks in decision-making applications like robotics and recommendation systems. A major limitation of the AMDP formalism, however, is…

Machine Learning · Statistics 2024-05-06 Sang Bin Moon , Abolfazl Hashemi

We study episodic reinforcement learning with fixed reward and transition functions, but with episode-dependent admissible action sets that are observed at the start of each episode. Performance is measured by cumulative regret against the…

Machine Learning · Computer Science 2026-05-18 Zijun Chen , Zihan Zhang

We consider the problem of online regret minimization in linear bandits with access to prior observations (offline data) from the underlying bandit model. There are numerous applications where extensive offline data is often available, such…

Machine Learning · Computer Science 2026-05-13 Sushant Vijayan , Arun Suggala , Karthikeyan Shanmugam , Soumyabrata Pal

We study reinforcement learning in non-episodic factored Markov decision processes (FMDPs). We propose two near-optimal and oracle-efficient algorithms for FMDPs. Assuming oracle access to an FMDP planner, they enjoy a Bayesian and a…

Machine Learning · Statistics 2020-06-09 Ziping Xu , Ambuj Tewari