English
Related papers

Related papers: Value Iteration for Long-run Average Reward in Mar…

200 papers

Regular Decision Processes (RDPs) are a recently introduced model that extends MDPs with non-Markovian dynamics and rewards. The non-Markovian behavior is restricted to depend on regular properties of the history. These can be specified…

Artificial Intelligence · Computer Science 2020-03-03 Eden Abadi , Ronen I. Brafman

We present a mean-variance policy iteration (MVPI) framework for risk-averse control in a discounted infinite horizon MDP optimizing the variance of a per-step reward random variable. MVPI enjoys great flexibility in that any policy…

Machine Learning · Computer Science 2022-04-08 Shangtong Zhang , Bo Liu , Shimon Whiteson

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

Partially observable Markov decision processes (POMDPs) provide an elegant mathematical framework for modeling complex decision and planning problems in stochastic domains in which states of the system are observable only indirectly, via a…

Artificial Intelligence · Computer Science 2011-06-02 M. Hauskrecht

This paper addresses a key limitation in existing counterfactual inference methods for Markov Decision Processes (MDPs). Current approaches assume a specific causal model to make counterfactuals identifiable. However, there are usually many…

Artificial Intelligence · Computer Science 2026-05-25 Jessica Lally , Milad Kazemi , Nicola Paoletti

We consider approximate dynamic programming for the infinite-horizon stationary $\gamma$-discounted optimal control problem formalized by Markov Decision Processes. While in the exact case it is known that there always exists an optimal…

Optimization and Control · Mathematics 2013-04-23 Boris Lesner , Bruno Scherrer

The Value Iteration (VI) algorithm is an iterative procedure to compute the value function of a Markov decision process, and is the basis of many reinforcement learning (RL) algorithms as well. As the error convergence rate of VI as a…

Machine Learning · Computer Science 2025-06-12 Jongmin Lee , Amin Rakhsha , Ernest K. Ryu , Amir-massoud Farahmand

In Markov Decision Processes (MDPs), the reward obtained in a state depends on the properties of the last state and action. This state dependency makes it difficult to reward more interesting long-term behaviors, such as always closing a…

Artificial Intelligence · Computer Science 2017-06-27 Ronen Brafman , Giuseppe De Giacomo , Fabio Patrizi

We consider the linear programming approach for constrained and unconstrained Markov decision processes (MDPs) under the long-run average cost criterion, where the class of MDPs in our study have Borel state spaces and discrete countable…

Optimization and Control · Mathematics 2021-04-20 Huizhen Yu

We consider the expressivity of Markov rewards in sequential decision making under uncertainty. We view reward functions in Markov Decision Processes (MDPs) as a means to characterize desired behaviors of agents. Assuming desired behaviors…

Artificial Intelligence · Computer Science 2023-07-25 Shuwa Miura

We consider a finite number of $N$ statistically equal agents, each moving on a finite set of states according to a continuous-time Markov Decision Process (MDP). Transition intensities of the agents and generated rewards depend not only on…

Probability · Mathematics 2025-09-23 Nicole Bäuerle , Sebastian Höfer

We study an approach to policy selection for large relational Markov Decision Processes (MDPs). We consider a variant of approximate policy iteration (API) that replaces the usual value-function learning step with a learning step in policy…

Artificial Intelligence · Computer Science 2011-09-13 A. Fern , R. Givan , S. Yoon

Howard's Policy Iteration (HPI) is a classic algorithm for solving Markov Decision Problems (MDPs). HPI uses a "greedy" switching rule to update from any non-optimal policy to a dominating one, iterating until an optimal policy is found.…

Artificial Intelligence · Computer Science 2025-05-05 Dibyangshu Mukherjee , Shivaram Kalyanakrishnan

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

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

We consider multiple-environment Markov decision processes (MEMDP), which consist of a finite set of MDPs over the same state space, representing different scenarios of transition structure and probability. The value of a strategy is the…

Logic in Computer Science · Computer Science 2025-04-23 Krishnendu Chatterjee , Laurent Doyen , Jean-François Raskin , Ocan Sankur

We study the problem of learning policies that maximize cumulative reward while satisfying safety constraints, even when the real environment differs from a simulator or nominal model. We focus on robust constrained Markov decision…

Machine Learning · Computer Science 2025-11-12 Sourav Ganguly , Arnob Ghosh

In this paper, we consider a Markov decision process (MDP), where the ego agent has a nominal objective to pursue while needs to hide its state from detection by an adversary. After formulating the problem, we first propose a value…

Systems and Control · Electrical Eng. & Systems 2019-08-22 Nan Li , Ilya Kolmanovsky , Anouck Girard

We consider a Markov control model in discrete time with countable both state space and action space. Using the value function of a suitable long-run average reward problem, we study various reachability/controllability problems. First, we…

Optimization and Control · Mathematics 2024-06-05 Daniel Avila , Mauricio Junca

The solution convergence of Markov Decision Processes (MDPs) can be accelerated by prioritized sweeping of states ranked by their potential impacts to other states. In this paper, we present new heuristics to speed up the solution…

Artificial Intelligence · Computer Science 2019-01-07 Shoubhik Debnath , Lantao Liu , Gaurav Sukhatme