English
Related papers

Related papers: Policy Optimization in Adversarial MDPs: Improved …

200 papers

In this paper, we consider the problem of optimization and learning for constrained and multi-objective Markov decision processes, for both discounted rewards and expected average rewards. We formulate the problems as zero-sum games where…

Optimization and Control · Mathematics 2021-03-05 Ather Gattami , Qinbo Bai , Vaneet Agarwal

We present an algorithm based on posterior sampling (aka Thompson sampling) that achieves near-optimal worst-case regret bounds when the underlying Markov Decision Process (MDP) is communicating with a finite, though unknown, diameter. Our…

Machine Learning · Computer Science 2020-04-01 Shipra Agrawal , Randy Jia

Although parallelism has been extensively used in reinforcement learning (RL), the quantitative effects of parallel exploration are not well understood theoretically. We study the benefits of simple parallel exploration for reward-free RL…

Machine Learning · Computer Science 2023-03-03 Pedro Cisneros-Velarde , Boxiang Lyu , Sanmi Koyejo , Mladen Kolar

It is well known that for any finite state Markov decision process (MDP) there is a memoryless deterministic policy that maximizes the expected reward. For partially observable Markov decision processes (POMDPs), optimal memoryless policies…

Optimization and Control · Mathematics 2016-02-16 Guido Montufar , Keyan Ghazi-Zahedi , Nihat Ay

Existing work on linear constrained Markov decision processes (CMDPs) has primarily focused on stochastic settings, where the losses and costs are either fixed or drawn from fixed distributions. However, such formulations are inherently…

Machine Learning · Computer Science 2026-05-13 Kihyun Yu , Seoungbin Bae , Dabeen Lee

In standard RL, a learner attempts to learn an optimal policy for a Markov Decision Process whose structure (e.g. state space) is known. In online model selection, a learner attempts to learn an optimal policy for an MDP knowing only that…

Machine Learning · Computer Science 2024-11-12 Alireza Masoumian , James R. Wright

Markov decision processes (MDPs) are widely used in modeling decision making problems in stochastic environments. However, precise specification of the reward functions in MDPs is often very difficult. Recent approaches have focused on…

Artificial Intelligence · Computer Science 2012-02-20 Eunsoo Oh , Kee-Eung Kim

Policy Iteration (PI) is a widely used family of algorithms to compute optimal policies for Markov Decision Problems (MDPs). We derive upper bounds on the running time of PI on Deterministic MDPs (DMDPs): the class of MDPs in which every…

Discrete Mathematics · Computer Science 2023-10-10 Ritesh Goenka , Eashan Gupta , Sushil Khyalia , Pratyush Agarwal , Mulinti Shaik Wajid , Shivaram Kalyanakrishnan

We address reinforcement learning problems with finite state and action spaces where the underlying MDP has some known structure that could be potentially exploited to minimize the exploration rates of suboptimal (state, action) pairs. For…

Machine Learning · Computer Science 2018-11-30 Jungseul Ok , Alexandre Proutiere , Damianos Tranos

We consider sequential decision making in a setting where regret is measured with respect to a set of stateful reference policies, and feedback is limited to observing the rewards of the actions performed (the so called "bandit" setting).…

Machine Learning · Computer Science 2014-07-30 Uriel Feige , Tomer Koren , Moshe Tennenholtz

Long-term fairness is an important factor of consideration in designing and deploying learning-based decision systems in high-stake decision-making contexts. Recent work has proposed the use of Markov Decision Processes (MDPs) to formulate…

Machine Learning · Computer Science 2022-10-25 Eric Yang Yu , Zhizhen Qin , Min Kyung Lee , Sicun Gao

We present an algorithm based on the \emph{Optimism in the Face of Uncertainty} (OFU) principle which is able to learn Reinforcement Learning (RL) modeled by Markov decision process (MDP) with finite state-action space efficiently. By…

Machine Learning · Computer Science 2020-01-01 Zihan Zhang , Xiangyang Ji

Model-based reinforcement learning (RL) can be effectively supported at scale through the use of world models. However, in practice, scaling such approaches remains fundamentally limited. A commonly recognized challenge is model bias and…

Machine Learning · Computer Science 2026-05-27 Xiaoyuan Cheng , Wenxuan Yuan , Zhancun Mu , Yuanzhao Zhang , Yiming Yang , Hai Wang , Zhuo Sun , Che Liu

We study the stochastic multi-armed bandit problem and design new policies that enjoy both worst-case optimality for expected regret and light-tailed risk for regret distribution. Specifically, our policy design (i) enjoys the worst-case…

Machine Learning · Statistics 2024-07-23 David Simchi-Levi , Zeyu Zheng , Feng Zhu

We propose novel classical and quantum online algorithms for learning finite-horizon and infinite-horizon average-reward Markov Decision Processes (MDPs). Our algorithms are based on a hybrid exploration-generative reinforcement learning…

Machine Learning · Computer Science 2025-08-12 Andris Ambainis , Joao F. Doriguello , Debbie Lim

Finding optimal policies which maximize long term rewards of Markov Decision Processes requires the use of dynamic programming and backward induction to solve the Bellman optimality equation. However, many real-world problems require…

Machine Learning · Computer Science 2023-01-10 Mridul Agarwal , Vaneet Aggarwal

This paper investigates the potential of quantum acceleration in addressing infinite horizon Markov Decision Processes (MDPs) to enhance average reward outcomes. We introduce an innovative quantum framework for the agent's engagement with…

Machine Learning · Computer Science 2025-05-28 Bhargav Ganguly , Yang Xu , Vaneet Aggarwal

We propose a new regret minimization algorithm for episodic sparse linear Markov decision process (SMDP) where the state-transition distribution is a linear function of observed features. The only previously known algorithm for SMDP…

Machine Learning · Statistics 2023-10-25 Wonyoung Kim , Garud Iyengar , Assaf Zeevi

This study considers the partial monitoring problem with $k$-actions and $d$-outcomes and provides the first best-of-both-worlds algorithms, whose regrets are favorably bounded both in the stochastic and adversarial regimes. In particular,…

Machine Learning · Computer Science 2022-10-11 Taira Tsuchiya , Shinji Ito , Junya Honda

We propose a new best-of-both-worlds algorithm for bandits with variably delayed feedback. In contrast to prior work, which required prior knowledge of the maximal delay $d_{\mathrm{max}}$ and had a linear dependence of the regret on it,…

Machine Learning · Computer Science 2024-05-29 Saeed Masoudian , Julian Zimmert , Yevgeny Seldin