English
Related papers

Related papers: Optimistic Policy Optimization with Bandit Feedbac…

200 papers

We study model-based reinforcement learning in an unknown finite communicating Markov decision process. We propose a simple algorithm that leverages a variance based confidence interval. We show that the proposed algorithm, UCRL-V, achieves…

Machine Learning · Computer Science 2019-12-12 Aristide Tossou , Debabrota Basu , Christos Dimitrakakis

We study the challenging exploration incentive problem in both bandit and reinforcement learning, where the rewards are scale-free and potentially unbounded, driven by real-world scenarios and differing from existing work. Past works in…

Machine Learning · Computer Science 2024-05-07 Mengfan Xu , Diego Klabjan

We develop several provably efficient model-free reinforcement learning (RL) algorithms for infinite-horizon average-reward Markov Decision Processes (MDPs). We consider both online setting and the setting with access to a simulator. In the…

Machine Learning · Computer Science 2023-06-29 Zihan Zhang , Qiaomin Xie

We study the $K$-armed contextual dueling bandit problem, a sequential decision making setting in which the learner uses contextual information to make two decisions, but only observes \emph{preference-based feedback} suggesting that one…

Machine Learning · Computer Science 2021-11-25 Aadirupa Saha , Akshay Krishnamurthy

In this paper, we propose a learning approach to analyze dynamic systems with asymmetric information structure. Instead of adopting a game theoretic setting, we investigate an online quadratic optimization problem driven by system noises…

Optimization and Control · Mathematics 2018-11-05 Cheng Tan , Wing Shing Wong

We present regret minimization algorithms for stochastic contextual MDPs under minimum reachability assumption, using an access to an offline least square regression oracle. We analyze three different settings: where the dynamics is known,…

Machine Learning · Computer Science 2023-01-24 Orin Levy , Yishay Mansour

We study online learning in finite-horizon episodic Markov decision processes (MDPs) under the challenging aggregate bandit feedback model, where the learner observes only the cumulative loss incurred in each episode, rather than individual…

Machine Learning · Computer Science 2025-10-28 Shinji Ito , Kevin Jamieson , Haipeng Luo , Arnab Maiti , Taira Tsuchiya

Proximal Policy Optimization (PPO) has become the predominant algorithm for on-policy reinforcement learning due to its scalability and empirical robustness across domains. However, there is a significant disconnect between the underlying…

In a low-rank linear bandit problem, the reward of an action (represented by a matrix of size $d_1 \times d_2$) is the inner product between the action and an unknown low-rank matrix $\Theta^*$. We propose an algorithm based on a novel…

Machine Learning · Statistics 2020-10-20 Yangyi Lu , Amirhossein Meisami , Ambuj Tewari

We consider model selection in stochastic bandit and reinforcement learning problems. Given a set of base learning algorithms, an effective model selection strategy adapts to the best learning algorithm in an online fashion. We show that by…

Machine Learning · Computer Science 2020-06-11 Yasin Abbasi-Yadkori , Aldo Pacchiano , My Phan

In this paper, we study a special bandit setting of online stochastic linear optimization, where only one-bit of information is revealed to the learner at each round. This problem has found many applications including online advertisement…

Machine Learning · Computer Science 2015-09-28 Lijun Zhang , Tianbao Yang , Rong Jin , Zhi-Hua Zhou

Optimal regret bounds for Multi-Armed Bandit problems are now well documented. They can be classified into two categories based on the growth rate with respect to the time horizon $T$: (i) small, distribution-dependent, bounds of order of…

Data Structures and Algorithms · Computer Science 2017-04-12 Arthur Flajolet , Patrick Jaillet

In this paper we consider the problem of online stochastic optimization of a locally smooth function under bandit feedback. We introduce the high-confidence tree (HCT) algorithm, a novel any-time $\mathcal{X}$-armed bandit algorithm, and…

Machine Learning · Statistics 2014-05-20 Mohammad Gheshlaghi Azar , Alessandro Lazaric , Emma Brunskill

We consider the problem of preference based reinforcement learning (PbRL), where, unlike traditional reinforcement learning, an agent receives feedback only in terms of a 1 bit (0/1) preference over a trajectory pair instead of absolute…

Machine Learning · Computer Science 2023-02-07 Aldo Pacchiano , Aadirupa Saha , Jonathan Lee

A crucial problem in reinforcement learning is learning the optimal policy. We study this in tabular infinite-horizon discounted Markov decision processes under the online setting. The existing algorithms either fail to achieve regret…

Machine Learning · Computer Science 2023-12-13 Xiang Ji , Gen Li

Reinforcement Learning(RL) with sparse rewards is a major challenge. We propose \emph{Hindsight Trust Region Policy Optimization}(HTRPO), a new RL algorithm that extends the highly successful TRPO algorithm with \emph{hindsight} to tackle…

Machine Learning · Computer Science 2021-05-18 Hanbo Zhang , Site Bai , Xuguang Lan , David Hsu , Nanning Zheng

Recent advances in Reinforcement Learning from Human Feedback (RLHF) have shown that KL-regularization plays a pivotal role in improving the efficiency of RL fine-tuning for large language models (LLMs). Despite its empirical advantage, the…

Machine Learning · Computer Science 2026-03-12 Heyang Zhao , Chenlu Ye , Wei Xiong , Quanquan Gu , Tong Zhang

Trust Region Policy Optimization (TRPO) is a popular and empirically successful policy search algorithm in reinforcement learning (RL). It iteratively solved the surrogate problem which restricts consecutive policies to be close to each…

Machine Learning · Computer Science 2021-10-27 Sahar Roostaie , Mohammad Mehdi Ebadzadeh

Combinatorial multi-armed bandits provide a fundamental online decision-making environment where a decision-maker interacts with an environment across $T$ time steps, each time selecting an action and learning the cost of that action. The…

Machine Learning · Computer Science 2026-04-13 Gerdus Benadè , Rathish Das , Thomas Lavastida

We develop the first general semi-bandit algorithm that simultaneously achieves $\mathcal{O}(\log T)$ regret for stochastic environments and $\mathcal{O}(\sqrt{T})$ regret for adversarial environments without knowledge of the regime or the…

Machine Learning · Computer Science 2019-09-27 Julian Zimmert , Haipeng Luo , Chen-Yu Wei