English
Related papers

Related papers: Risk-averse optimization of total rewards in Marko…

200 papers

We propose a general framework for entropy-regularized average-reward reinforcement learning in Markov decision processes (MDPs). Our approach is based on extending the linear-programming formulation of policy optimization in MDPs to…

Machine Learning · Computer Science 2017-05-23 Gergely Neu , Anders Jonsson , Vicenç Gómez

Optimal control in non-stationary Markov decision processes (MDP) is a challenging problem. The aim in such a control problem is to maximize the long-term discounted reward when the transition dynamics or the reward function can change over…

Applications · Statistics 2017-03-03 Taposh Banerjee , Miao Liu , Jonathan P. How

Optimizing static risk-averse objectives in Markov decision processes is difficult because they do not admit standard dynamic programming equations common in Reinforcement Learning (RL) algorithms. Dynamic programming decompositions that…

Optimization and Control · Mathematics 2024-07-04 Jia Lin Hau , Erick Delage , Mohammad Ghavamzadeh , Marek Petrik

Interval Markov decision processes are a class of Markov models where the transition probabilities between the states belong to intervals. In this paper, we study the problem of efficient estimation of the optimal policies in Interval…

Systems and Control · Electrical Eng. & Systems 2023-09-19 Saber Jafarpour , Samuel Coogan

An optimal feedback controller for a given Markov decision process (MDP) can in principle be synthesized by value or policy iteration. However, if the system dynamics and the reward function are unknown, a learning agent must discover an…

Machine Learning · Computer Science 2019-07-19 Boris Belousov , Jan Peters

Decision making under uncertain environments in the maximization of expected reward while minimizing its risk is one of the ubiquitous problems in many subjects. Here, we introduce a novel problem setting in stochastic bandit optimization…

Machine Learning · Computer Science 2025-10-27 Shunta Nonaga , Koji Tabata , Yuta Mizuno , Tamiki Komatsuzaki

We study reinforcement learning for continuous-time Markov decision processes (MDPs) in the finite-horizon episodic setting. In contrast to discrete-time MDPs, the inter-transition times of a continuous-time MDP are exponentially…

Machine Learning · Computer Science 2023-10-04 Xuefeng Gao , Xun Yu Zhou

We consider risk-sensitive Markov decision processes (MDPs), where the MDP model is influenced by a parameter which takes values in a compact metric space. We identify sufficient conditions under which small perturbations in the model…

Optimization and Control · Mathematics 2022-09-28 Shiping Shao , Abhishek Gupta , William B. Haskell

A Markov decision process (MDP) framework is adopted to represent ensemble control of devices with cyclic energy consumption patterns, e.g., thermostatically controlled loads. Specifically we utilize and develop the class of MDP models…

Systems and Control · Computer Science 2017-10-24 Michael Chertkov , Vladimir Y. Chernyak , Deepjyoti Deka

Model checking undiscounted reachability and expected-reward properties on Markov decision processes (MDPs) is key for the verification of systems that act under uncertainty. Popular algorithms are policy iteration and variants of value…

Logic in Computer Science · Computer Science 2023-01-25 Arnd Hartmanns , Sebastian Junges , Tim Quatmann , Maximilian Weininger

Recent research has revived and amplified interest in algorithms for undiscounted average reward reinforcement learning in infinite-horizon, non-episodic (continuing) tasks. Semi-Markov decision processes (SMDPs) are of particular interest.…

Machine Learning · Computer Science 2026-05-27 Erel Shtossel , Alicia Vidler , Uri Shaham , Gal A. Kaminka

We consider the problem of constrained Markov Decision Process (CMDP) where an agent interacts with a unichain Markov Decision Process. At every interaction, the agent obtains a reward. Further, there are $K$ cost functions. The agent aims…

Machine Learning · Computer Science 2022-06-22 Mridul Agarwal , Qinbo Bai , Vaneet Aggarwal

Current critic-less RLHF methods aggregate multi-objective rewards via an arithmetic mean, leaving them vulnerable to constraint neglect: high-magnitude success in one objective can numerically offset critical failures in others (e.g.,…

Machine Learning · Computer Science 2026-05-08 Ivan Montero , Tomasz Jurczyk , Bhuwan Dhingra

Markov decision processes (MDPs) is viewed as an optimization of an objective function over certain linear operators over general function spaces. A new existence result is established for the existence of optimal policies in general MDPs,…

Machine Learning · Computer Science 2026-04-01 Abhishek Gupta , Aditya Mahajan

A classic solution technique for Markov decision processes (MDP) and stochastic games (SG) is value iteration (VI). Due to its good practical performance, this approximative approach is typically preferred over exact techniques, even though…

Artificial Intelligence · Computer Science 2023-04-21 Jan Křetínský , Tobias Meggendorfer , Maximilian Weininger

We consider the infinite-horizon linear Markov Decision Processes (MDPs), where the transition probabilities of the dynamic model can be linearly parameterized with the help of a predefined low-dimensional feature mapping. While the…

Machine Learning · Computer Science 2023-10-19 Yu-Heng Hung , Ping-Chun Hsieh , Akshay Mete , P. R. Kumar

In order to model risk aversion in reinforcement learning, an emerging line of research adapts familiar algorithms to optimize coherent risk functionals, a class that includes conditional value-at-risk (CVaR). Because optimizing the…

Machine Learning · Computer Science 2021-03-09 Audrey Huang , Liu Leqi , Zachary C. Lipton , Kamyar Azizzadenesheli

The window mean-payoff objective strengthens the classical mean-payoff objective by computing the mean-payoff over a finite window that slides along an infinite path. Two variants have been considered: in one variant, the maximum window…

Computer Science and Game Theory · Computer Science 2025-01-10 Pranshu Gaba , Shibashis Guha

We propose and study a general framework for regularized Markov decision processes (MDPs) where the goal is to find an optimal policy that maximizes the expected discounted total reward plus a policy regularization term. The extant…

Machine Learning · Statistics 2019-10-22 Xiang Li , Wenhao Yang , Zhihua Zhang

In classical Markov Decision Processes (MDPs), action costs and transition probabilities are assumed to be known, although an accurate estimation of these parameters is often not possible in practice. This study addresses MDPs under cost…

Optimization and Control · Mathematics 2019-06-24 Merve Merakli , Simge Kucukyavuz