English
Related papers

Related papers: Non-Rectangular Average-Reward Robust MDPs: Optima…

200 papers

Strong worst-case performance bounds for episodic reinforcement learning exist but fortunately in practice RL algorithms perform much better than such bounds would predict. Algorithms and theory that provide strong problem-dependent bounds…

Machine Learning · Computer Science 2019-11-05 Andrea Zanette , Emma Brunskill

We study the evaluation of a policy under best- and worst-case perturbations to a Markov decision process (MDP), using transition observations from the original MDP, whether they are generated under the same or a different policy. This is…

Artificial Intelligence · Computer Science 2024-11-05 Andrew Bennett , Nathan Kallus , Miruna Oprescu , Wen Sun , Kaiwen Wang

Regular decision processes (RDPs) are a subclass of non-Markovian decision processes where the transition and reward functions are guarded by some regular property of the past (a lookback). While RDPs enable intuitive and succinct…

Logic in Computer Science · Computer Science 2023-12-15 Ernst Moritz Hahn , Mateo Perez , Sven Schewe , Fabio Somenzi , Ashutosh Trivedi , Dominik Wojtczak

We tackle average-reward infinite-horizon POMDPs with an unknown transition model but a known observation model, a setting that has been previously addressed in two limiting ways: (i) frequentist methods relying on suboptimal stochastic…

Machine Learning · Computer Science 2025-09-09 Alessio Russo , Alberto Maria Metelli , Marcello Restelli

We propose an epoch-based reinforcement learning algorithm for infinite-horizon average-cost Markov decision processes (MDPs) that leverages a partial order over a policy class. In this structure, $\pi' \leq \pi$ if data collected under…

Machine Learning · Statistics 2025-08-07 Zhongjun Zhang , Shipra Agrawal , Ilan Lobel , Sean R. Sinclair , Christina Lee Yu

We consider online learning in episodic loop-free Markov decision processes (MDPs), where the loss function can change arbitrarily between episodes, and the transition function is not known to the learner. We show…

Machine Learning · Computer Science 2019-05-21 Aviv Rosenberg , Yishay Mansour

This paper investigates the challenges of optimal online policy learning under missing data. State-of-the-art algorithms implicitly assume that rewards are always observable. I show that when rewards are missing at random, the Upper…

Econometrics · Economics 2025-07-29 Filippo Palomba

Most reinforcement learning methods are based upon the key assumption that the transition dynamics and reward functions are fixed, that is, the underlying Markov decision process is stationary. However, in many real-world applications, this…

Machine Learning · Computer Science 2020-09-23 Yash Chandak , Georgios Theocharous , Shiv Shankar , Martha White , Sridhar Mahadevan , Philip S. Thomas

The Reward-Biased Maximum Likelihood Estimate (RBMLE) for adaptive control of Markov chains was proposed to overcome the central obstacle of what is variously called the fundamental "closed-identifiability problem" of adaptive control, the…

Machine Learning · Computer Science 2021-05-18 Akshay Mete , Rahul Singh , Xi Liu , P. R. Kumar

Robust Markov Decision Processes (MDPs) are receiving much attention in learning a robust policy which is less sensitive to environment changes. There are an increasing number of works analyzing sample-efficiency of robust MDPs. However,…

Machine Learning · Statistics 2023-09-13 Wenhao Yang , Han Wang , Tadashi Kozuno , Scott M. Jordan , Zhihua Zhang

In this paper, we investigate system theoretic properties of transient average constrained economic model predictive control (MPC) without terminal constraints. We show that the optimal open-loop solution passes by the optimal steady-state…

Systems and Control · Electrical Eng. & Systems 2020-10-21 Mario Rosenfelder , Johannes Köhler , Frank Allgöwer

We introduce data-driven decision-making algorithms that achieve state-of-the-art \emph{dynamic regret} bounds for non-stationary bandit settings. These settings capture applications such as advertisement allocation, dynamic pricing, and…

Machine Learning · Computer Science 2021-03-19 Wang Chi Cheung , David Simchi-Levi , Ruihao Zhu

The online Markov decision process (MDP) is a generalization of the classical Markov decision process that incorporates changing reward functions. In this paper, we propose practical online MDP algorithms with policy iteration and…

Machine Learning · Computer Science 2015-10-16 Yao Ma , Hao Zhang , Masashi Sugiyama

We consider the setting of iterative learning control, or model-based policy learning in the presence of uncertain, time-varying dynamics. In this setting, we propose a new performance metric, planning regret, which replaces the standard…

Machine Learning · Computer Science 2021-03-01 Naman Agarwal , Elad Hazan , Anirudha Majumdar , Karan Singh

We present a new algorithm based on posterior sampling for learning in Constrained Markov Decision Processes (CMDP) in the infinite-horizon undiscounted setting. The algorithm achieves near-optimal regret bounds while being advantageous…

Machine Learning · Computer Science 2024-05-30 Danil Provodin , Maurits Kaptein , Mykola Pechenizkiy

The robust $\phi$-regularized Markov Decision Process (RRMDP) framework focuses on designing control policies that are robust against parameter uncertainties due to mismatches between the simulator (nominal) model and real-world settings.…

Machine Learning · Computer Science 2024-05-10 Kishan Panaganti , Adam Wierman , Eric Mazumdar

Policy optimization methods are popular reinforcement learning algorithms in practice. Recent works have built theoretical foundation for them by proving $\sqrt{T}$ regret bounds even when the losses are adversarial. Such bounds are tight…

Machine Learning · Computer Science 2023-02-21 Christoph Dann , Chen-Yu Wei , Julian Zimmert

We study the regret guarantee for risk-sensitive reinforcement learning (RSRL) via distributional reinforcement learning (DRL) methods. In particular, we consider finite episodic Markov decision processes whose objective is the entropic…

Machine Learning · Computer Science 2024-01-26 Hao Liang , Zhi-Quan Luo

Markov decision processes (MDPs) are used to model a wide variety of applications ranging from game playing over robotics to finance. Their optimal policy typically maximizes the expected sum of rewards given at each step of the decision…

Machine Learning · Computer Science 2025-05-26 Maximilian Nägele , Jan Olle , Thomas Fösel , Remmy Zen , Florian Marquardt

We study regret minimization for reinforcement learning (RL) in Latent Markov Decision Processes (LMDPs) with context in hindsight. We design a novel model-based algorithmic framework which can be instantiated with both a model-optimistic…

Machine Learning · Computer Science 2023-05-23 Runlong Zhou , Ruosong Wang , Simon S. Du