English
Related papers

Related papers: Solving POMDPs by Searching in Policy Space

200 papers

Partially Observable Markov Decision Processes (POMDPs) are a fundamental framework for decision-making under uncertainty and partial observability. Since in general optimal policies may require infinite memory, they are hard to implement…

Artificial Intelligence · Computer Science 2026-04-30 Muqsit Azeem , Debraj Chakraborty , Sudeep Kanav , Jan Kretinsky

Monotonic Partially Observable Markov Decision Processes (POMDPs), where the system state progressively decreases until a restorative action is performed, can be used to model sequential repair problems effectively. This paper considers the…

Machine Learning · Computer Science 2025-09-17 Manav Vora , Jonas Liang , Michael N. Grussing , Melkior Ornik

Partially observable Markov decision processes (POMDPs) provide a modeling framework for a variety of sequential decision making under uncertainty scenarios in artificial intelligence (AI). Since the states are not directly observable in a…

Systems and Control · Computer Science 2019-05-21 Mohamadreza Ahmadi , Nils Jansen , Bo Wu , Ufuk Topcu

Decentralized partially observable Markov decision processes (Dec-POMDPs) are rich models for cooperative decision-making under uncertainty, but are often intractable to solve optimally (NEXP-complete). The transition and observation…

Artificial Intelligence · Computer Science 2012-10-19 Jilles S. Dibangoye , Christopher Amato , Arnoud Doniec

We study model-based learning of finite-window policies in tabular partially observable Markov decision processes (POMDPs). A common approach to learning under partial observability is to approximate unbounded history dependencies using…

Machine Learning · Computer Science 2026-04-02 Philip Jordan , Maryam Kamgarpour

Partially observable Markov decision processes (POMDPs) provide a principled framework for sequential planning in uncertain single agent settings. An extension of POMDPs to multiagent settings, called interactive POMDPs (I-POMDPs), replaces…

Artificial Intelligence · Computer Science 2014-01-16 Prashant Doshi , Piotr J. Gmytrasiewicz

The main goal in task planning is to build a sequence of actions that takes an agent from an initial state to a goal state. In robotics, this is particularly difficult because actions usually have several possible results, and sensors are…

Artificial Intelligence · Computer Science 2021-04-12 Sergio A. Serrano , Elizabeth Santiago , Jose Martinez-Carranza , Eduardo Morales , L. Enrique Sucar

Uncertain partially observable Markov decision processes (uPOMDPs) allow the probabilistic transition and observation functions of standard POMDPs to belong to a so-called uncertainty set. Such uncertainty, referred to as epistemic…

Artificial Intelligence · Computer Science 2021-11-02 Murat Cubuktepe , Nils Jansen , Sebastian Junges , Ahmadreza Marandi , Marnix Suilen , Ufuk Topcu

We consider the problem of approximate belief-state monitoring using particle filtering for the purposes of implementing a policy for a partially-observable Markov decision process (POMDP). While particle filtering has become a widely-used…

Artificial Intelligence · Computer Science 2013-01-14 Pascal Poupart , Luis E. Ortiz , Craig Boutilier

In the theory of Partially Observed Markov Decision Processes (POMDPs), existence of optimal policies have in general been established via converting the original partially observed stochastic control problem to a fully observed one on the…

Optimization and Control · Mathematics 2022-01-11 Ali Devran Kara , Serdar Yuksel

A nonparametric approach for policy learning for POMDPs is proposed. The approach represents distributions over the states, observations, and actions as embeddings in feature spaces, which are reproducing kernel Hilbert spaces.…

Machine Learning · Computer Science 2012-10-19 Yu Nishiyama , Abdeslam Boularias , Arthur Gretton , Kenji Fukumizu

Partially observable Markov decision processes (POMDPs) provide a modeling framework for autonomous decision making under uncertainty and imperfect sensing, e.g. robot manipulation and self-driving cars. However, optimal control of POMDPs…

Artificial Intelligence · Computer Science 2020-01-22 Mohamadreza Ahmadi , Rangoli Sharan , Joel W. Burdick

Acting to complete tasks in stochastic partially observable domains is an important problem in artificial intelligence, and is often formulated as a goal-based POMDP. Goal-based POMDPs can be solved using the RTDP-BEL algorithm, that…

Artificial Intelligence · Computer Science 2024-10-10 Guy Shani

The synthesis problem for partially observable Markov decision processes (POMDPs) is to compute a policy that satisfies a given specification. Such policies have to take the full execution history of a POMDP into account, rendering the…

Artificial Intelligence · Computer Science 2020-07-20 Leonore Winterer , Ralf Wimmer , Nils Jansen , Bernd Becker

We present an A*-based algorithm to compute policies for finite-horizon Dec-POMDPs. Our goal is to sacrifice optimality in favor of scalability for larger horizons. The main ingredients of our approach are (1) using clustered sliding window…

Artificial Intelligence · Computer Science 2024-05-10 Wietze Koops , Sebastian Junges , Nils Jansen

Optimally solving decentralized decision-making problems modeled as Dec-POMDPs is known to be NEXP-complete. These optimal solutions are policies based on the entire history of observations and actions of an agent. However, some…

Multiagent Systems · Computer Science 2026-04-13 Amit Sinha , Matthieu Geist , Aditya Mahajan

This paper aims to establish an entropy-regularized value-based reinforcement learning method that can ensure the monotonic improvement of policies at each policy update. Unlike previously proposed lower-bounds on policy improvement in…

Machine Learning · Computer Science 2020-08-26 Lingwei Zhu , Takamitsu Matsubara

Partially Observable Markov Decision Processes (POMDPs) are a powerful framework for planning under uncertainty. They allow to model state uncertainty as a belief probability distribution. Approximate solvers based on Monte Carlo sampling…

Artificial Intelligence · Computer Science 2024-03-01 Daniele Meli , Alberto Castellini , Alessandro Farinelli

Our goal is to compute a policy that guarantees improved return over a baseline policy even when the available MDP model is inaccurate. The inaccurate model may be constructed, for example, by system identification techniques when the true…

Optimization and Control · Mathematics 2015-06-17 Yinlam Chow , Marek Petrik , Mohammad Ghavamzadeh

In this paper, we propose a new policy iteration algorithm to compute the value function and the optimal controls of continuous time stochastic control problems. The algorithm relies on successive approximations using linear-quadratic…

Optimization and Control · Mathematics 2024-09-09 Dylan Possamaï , Ludovic Tangpi