English
Related papers

Related papers: Variance-Constrained Actor-Critic Algorithms for D…

200 papers

Value-at-risk (VaR), also known as quantile, is a crucial risk measure in finance and other fields. However, optimizing VaR metrics in Markov decision processes (MDPs) is challenging because VaR is non-additive and the traditional dynamic…

Optimization and Control · Mathematics 2025-07-31 Li Xia , Jinyan Pan

In this work, we study the problem of finding robust and safe policies in Robust Constrained Average-Cost Markov Decision Processes (RCMDPs). A key challenge in this setting is the lack of strong duality, which prevents the direct use of…

Machine Learning · Computer Science 2025-11-11 Anirudh Satheesh , Sooraj Sathish , Swetha Ganesh , Keenan Powell , Vaneet Aggarwal

This paper addresses objectives tailored to the risk-averse optimization of accumulated rewards in Markov decision processes (MDPs). The studied objectives require maximizing the expected value of the accumulated rewards minus a penalty…

Logic in Computer Science · Computer Science 2024-07-10 Christel Baier , Jakob Piribauer , Maximilian Starke

We study the risk-sensitive exponential cost MDP formulation and develop a trajectory-based gradient algorithm to find the stationary point of the cost associated with a set of parameterized policies. We derive a formula that can be used to…

Systems and Control · Electrical Eng. & Systems 2022-08-31 Mehrdad Moharrami , Yashaswini Murthy , Arghyadip Roy , R. Srikant

We present the first finite time global convergence analysis of policy gradient in the context of infinite horizon average reward Markov decision processes (MDPs). Specifically, we focus on ergodic tabular MDPs with finite state and action…

Machine Learning · Computer Science 2024-03-12 Navdeep Kumar , Yashaswini Murthy , Itai Shufaro , Kfir Y. Levy , R. Srikant , Shie Mannor

Option-critic learning is a general-purpose reinforcement learning (RL) framework that aims to address the issue of long term credit assignment by leveraging temporal abstractions. However, when dealing with extended timescales, discounting…

Machine Learning · Computer Science 2019-11-21 Akshay Dharmavaram , Matthew Riemer , Shalabh Bhatnagar

In this paper, we consider the risk-sensitive cost criterion with exponentiated costs for Markov decision processes and develop a model-free policy gradient algorithm in this setting. Unlike additive cost criteria such as average or…

Machine Learning · Computer Science 2025-08-05 Soumyajit Guin , Vivek S. Borkar , Shalabh Bhatnagar

Several recent works have focused on carrying out non-asymptotic convergence analyses for AC algorithms. Recently, a two-timescale critic-actor algorithm has been presented for the discounted cost setting in the look-up table case where the…

Machine Learning · Computer Science 2025-09-01 Prashansa Panda , Shalabh Bhatnagar

In this paper we present an algorithm to compute risk averse policies in Markov Decision Processes (MDP) when the total cost criterion is used together with the average value at risk (AVaR) metric. Risk averse policies are needed when large…

Optimization and Control · Mathematics 2016-02-17 Stefano Carpin , Yin-Lam Chow , Marco Pavone

Safety in stochastic control systems, which are subject to random noise with a known probability distribution, aims to compute policies that satisfy predefined operational constraints with high confidence throughout the uncertain evolution…

Systems and Control · Electrical Eng. & Systems 2025-11-12 Saber Omidi , Marek Petrik , Se Young Yoon , Momotaz Begum

We propose a novel actor-critic algorithm with guaranteed convergence to an optimal policy for a discounted reward Markov decision process. The actor incorporates a descent direction that is motivated by the solution of a certain non-linear…

Machine Learning · Computer Science 2015-07-30 Prashanth L. A. , H. L. Prasad , Shalabh Bhatnagar , Prakash Chandra

Dynamic optimization of mean and variance in Markov decision processes (MDPs) is a long-standing challenge caused by the failure of dynamic programming. In this paper, we propose a new approach to find the globally optimal policy for…

Optimization and Control · Mathematics 2023-02-28 Li Xia , Shuai Ma

Several authors have recently developed risk-sensitive policy gradient methods that augment the standard expected cost minimization problem with a measure of variability in cost. These studies have focused on specific risk-measures, such as…

Artificial Intelligence · Computer Science 2015-06-09 Aviv Tamar , Yinlam Chow , Mohammad Ghavamzadeh , Shie Mannor

We study the general approach to accelerating the convergence of the most widely used solution method of Markov decision processes with the total expected discounted reward. Inspired by the monotone behavior of the contraction mappings in…

Optimization and Control · Mathematics 2008-03-28 Oleksandr Shlakhter , Chi-Guhn Lee , Dmitry Khmelev , Nasser Jaber

Managing risk in dynamic decision problems is of cardinal importance in many fields such as finance and process control. The most common approach to defining risk is through various variance related criteria such as the Sharpe Ratio or the…

Machine Learning · Computer Science 2012-07-03 Dotan Di Castro , Aviv Tamar , Shie Mannor

We study average-reward Markov decision processes (AMDPs) and develop novel first-order methods with strong theoretical guarantees for both policy optimization and policy evaluation. Compared with intensive research efforts in finite sample…

Machine Learning · Computer Science 2024-10-01 Tianjiao Li , Feiyang Wu , Guanghui Lan

This paper investigates infinite-horizon average reward Constrained Markov Decision Processes (CMDPs) with general parametrization. We propose a Primal-Dual Natural Actor-Critic algorithm that adeptly manages constraints while ensuring a…

Machine Learning · Computer Science 2025-12-11 Yang Xu , Swetha Ganesh , Washim Uddin Mondal , Qinbo Bai , Vaneet Aggarwal

We present an actor-critic framework for MDPs where the objective is the variance-adjusted expected return. Our critic uses linear function approximation, and we extend the concept of compatible features to the variance-adjusted setting. We…

Machine Learning · Statistics 2013-10-15 Aviv Tamar , Shie Mannor

Policy gradient methods are reinforcement learning algorithms that adapt a parameterized policy by following a performance gradient estimate. Conventional policy gradient methods use Monte-Carlo techniques to estimate the gradient, which…

Machine Learning · Computer Science 2026-05-01 Mohammad Ghavamzadeh , Yaakov Engel , Michal Valko

Constrained decision-making is essential for designing safe policies in real-world control systems, yet simulated environments often fail to capture real-world adversities. We consider the problem of learning a policy that will maximize the…

Machine Learning · Computer Science 2026-02-10 Sourav Ganguly , Kishan Panaganti , Arnob Ghosh , Adam Wierman