English
Related papers

Related papers: Dynamically Augmented CVaR for MDPs

200 papers

Robust Markov decision processes (RMDPs) provide a promising framework for computing reliable policies in the face of model errors. Many successful reinforcement learning algorithms build on variations of policy-gradient methods, but…

Machine Learning · Computer Science 2024-05-15 Qiuhao Wang , Chin Pang Ho , Marek Petrik

Robust Markov decision processes (RMDPs) extend standard Markov decision processes (MDPs) to account for uncertainty in the transition probabilities. RMDPs have an uncertainty set that defines a set of possible transition functions, each of…

Logic in Computer Science · Computer Science 2026-04-30 Marnix Suilen , Guillermo A. Pérez

The problem of constrained Markov decision process (CMDP) is investigated, where an agent aims to maximize the expected accumulated discounted reward subject to multiple constraints on its utilities/costs. A new primal-dual approach is…

Optimization and Control · Mathematics 2021-10-22 Tianjiao Li , Ziwei Guan , Shaofeng Zou , Tengyu Xu , Yingbin Liang , Guanghui Lan

We study the minimization of a spectral risk measure of the total discounted cost generated by a Markov Decision Process (MDP) over a finite or infinite planning horizon. The MDP is assumed to have Borel state and action spaces and the cost…

Optimization and Control · Mathematics 2025-10-16 Nicole Bäuerle , Alexander Glauner

A popular perspective in Reinforcement learning (RL) casts the problem as probabilistic inference on a graphical model of the Markov decision process (MDP). The core object of study is the probability of each state-action pair being visited…

Machine Learning · Computer Science 2023-11-23 Jean Tarbouriech , Tor Lattimore , Brendan O'Donoghue

Conditional Value-at-Risk (CVaR) is a central tail-risk measure in stochastic structural mechanics, yet its accurate evaluation under high-dimensional, spatially correlated material uncertainty remains computationally prohibitive for…

Machine Learning · Statistics 2026-02-11 Alireza Tabarraei

We consider large-scale Markov decision processes (MDPs) with parameter uncertainty, under the robust MDP paradigm. Previous studies showed that robust MDPs, based on a minimax approach to handle uncertainty, can be solved using dynamic…

Machine Learning · Computer Science 2013-06-27 Aviv Tamar , Huan Xu , Shie Mannor

Despite the success of Gaussian process based Model Predictive Control (MPC) in robotic control, its applicability scope is greatly hindered by multimodal disturbances that are prevalent in real-world settings. Here we propose a novel…

Systems and Control · Electrical Eng. & Systems 2025-02-11 Jingyi Wu , Chao Ning

Approximate dynamic programming is a popular method for solving large Markov decision processes. This paper describes a new class of approximate dynamic programming (ADP) methods- distributionally robust ADP-that address the curse of…

Machine Learning · Statistics 2012-05-22 Marek Petrik

Considering non-stationary environments in online optimization enables decision-maker to effectively adapt to changes and improve its performance over time. In such cases, it is favorable to adopt a strategy that minimizes the negative…

Systems and Control · Electrical Eng. & Systems 2024-04-05 Siyi Wang , Zifan Wang , Xinlei Yi , Michael M. Zavlanos , Karl H. Johansson , Sandra Hirche

When transferring a control policy from simulation to a physical system, the policy needs to be robust to variations in the dynamics to perform well. Commonly, the optimal policy overfits to the approximate model and the corresponding…

Machine Learning · Computer Science 2021-05-27 Michael Lutter , Shie Mannor , Jan Peters , Dieter Fox , Animesh Garg

We consider a discounted cost constrained Markov decision process (CMDP) policy optimization problem, in which an agent seeks to maximize a discounted cumulative reward subject to a number of constraints on discounted cumulative utilities.…

Optimization and Control · Mathematics 2024-11-21 Sihan Zeng , Thinh T. Doan , Justin Romberg

Instead of controlling "symmetric" risks measured by central moments of investment return or terminal wealth, more and more portfolio models have shifted their focus to manage "asymmetric" downside risks that the investment return is below…

Portfolio Management · Quantitative Finance 2014-02-17 Jianjun Gao , Ke Zhou , Duan Li , Xiren Cao

We develop a generic policy gradient method with the global optimality guarantee for robust Markov Decision Processes (MDPs). While policy gradient methods are widely used for solving dynamic decision problems due to their scalable and…

Machine Learning · Computer Science 2024-11-01 Qiuhao Wang , Shaohang Xu , Chin Pang Ho , Marek Petrik

In this work, we study the problem of actively classifying the attributes of dynamical systems characterized as a finite set of Markov decision process (MDP) models. We are interested in finding strategies that actively interact with the…

Systems and Control · Electrical Eng. & Systems 2023-01-06 Bo Wu , Niklas Lauffer , Mohamadreza Ahmadi , Suda Bharadwaj , Zhe Xu , Ufuk Topcu

We study an approach to offline reinforcement learning (RL) based on optimally solving finitely-represented MDPs derived from a static dataset of experience. This approach can be applied on top of any learned representation and has the…

Machine Learning · Computer Science 2025-02-06 Aayam Shrestha , Stefan Lee , Prasad Tadepalli , Alan Fern

Robust Markov decision processes (MDPs) are used for applications of dynamic optimization in uncertain environments and have been studied extensively. Many of the main properties and algorithms of MDPs, such as value iteration and policy…

Optimization and Control · Mathematics 2023-12-14 Julien Grand-Clément , Marek Petrik

A novel reinforcement learning scheme to synthesize policies for continuous-space Markov decision processes (MDPs) is proposed. This scheme enables one to apply model-free, off-the-shelf reinforcement learning algorithms for finite MDPs to…

Systems and Control · Electrical Eng. & Systems 2020-03-03 Abolfazl Lavaei , Fabio Somenzi , Sadegh Soudjani , Ashutosh Trivedi , Majid Zamani

Safety exploration can be regarded as a constrained Markov decision problem where the expected long-term cost is constrained. Previous off-policy algorithms convert the constrained optimization problem into the corresponding unconstrained…

Machine Learning · Computer Science 2024-10-28 Hengrui Zhang , Youfang Lin , Sheng Han , Shuo Wang , Kai Lv

Designing sample-efficient and computationally feasible reinforcement learning (RL) algorithms is particularly challenging in environments with large or infinite state and action spaces. In this paper, we advance this effort by presenting…

Machine Learning · Computer Science 2024-10-04 Zakaria Mhammedi