中文
相关论文

相关论文: The Wasserstein Believer: Learning Belief Updates …

200 篇论文

Partially Observable Markov Decision Processes (POMDPs) provide a rich framework for sequential decision-making under uncertainty in stochastic domains. However, solving a POMDP is often intractable except for small problems due to their…

人工智能 · 计算机科学 2014-01-16 Stéphane Ross , Joelle Pineau , Sébastien Paquet , Brahim Chaib-draa

We study the model-based undiscounted reinforcement learning for partially observable Markov decision processes (POMDPs). The oracle we consider is the optimal policy of the POMDP with a known environment in terms of the average reward over…

机器学习 · 计算机科学 2022-07-19 Yi Xiong , Ningyuan Chen , Xuefeng Gao , Xiang Zhou

In many real-world decision problems there is partially observed, hidden or latent information that remains fixed throughout an interaction. Such decision problems can be modeled as Latent Markov Decision Processes (LMDPs), where a latent…

机器学习 · 计算机科学 2024-06-27 Jeongyeol Kwon , Shie Mannor , Constantine Caramanis , Yonathan Efroni

We consider a distributionally robust Partially Observable Markov Decision Process (DR-POMDP), where the distribution of the transition-observation probabilities is unknown at the beginning of each decision period, but their realizations…

最优化与控制 · 数学 2020-12-09 Hideaki Nakao , Ruiwei Jiang , Siqian Shen

Partially observable Markov decision processes (POMDP) are a useful model for decision-making under partial observability and stochastic actions. Partially Observable Monte-Carlo Planning is an online algorithm for deciding on the next…

人工智能 · 计算机科学 2023-10-05 Oded Blumenthal , Guy Shani

Partially observable Markov decision processes (POMDPs) rely on the key assumption that probability distributions are precisely known. Robust POMDPs (RPOMDPs) alleviate this concern by defining imprecise probabilities, referred to as…

人工智能 · 计算机科学 2024-07-30 Eline M. Bovy , Marnix Suilen , Sebastian Junges , Nils Jansen

This paper studies the sample-efficiency of learning in Partially Observable Markov Decision Processes (POMDPs), a challenging problem in reinforcement learning that is known to be exponentially hard in the worst-case. Motivated by…

机器学习 · 计算机科学 2023-07-07 Jiacheng Guo , Minshuo Chen , Huan Wang , Caiming Xiong , Mengdi Wang , Yu Bai

This paper delves into the problem of safe reinforcement learning (RL) in a partially observable environment with the aim of achieving safe-reachability objectives. In traditional partially observable Markov decision processes (POMDP),…

机器学习 · 计算机科学 2023-12-04 Xiaoyuan Cheng , Boli Chen , Liz Varga , Yukun Hu

Partially observable Markov decision processes (POMDPs) are widely used in probabilistic planning problems in which an agent interacts with an environment using noisy and imprecise sensors. We study a setting in which the sensors are only…

人工智能 · 计算机科学 2017-10-03 Krishnendu Chatterjee , Martin Chmelik , Ufuk Topcu

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…

人工智能 · 计算机科学 2021-11-02 Murat Cubuktepe , Nils Jansen , Sebastian Junges , Ahmadreza Marandi , Marnix Suilen , Ufuk Topcu

Partially Observable Markov Decision Processes (POMDPs) are fundamental to many real-world applications. Although reinforcement learning (RL) has shown success in fully observable domains, learning policies from traces in partially…

机器学习 · 计算机科学 2025-08-05 Yuly Wu , Jiamou Liu , Libo Zhang

In Partially Observable Markov Decision Processes (POMDPs), maintaining and updating belief distributions over possible underlying states provides a principled way to summarize action-observation history for effective decision-making under…

机器学习 · 计算机科学 2025-10-27 Yunuo Zhang , Baiting Luo , Ayan Mukhopadhyay , Gabor Karsai , Abhishek Dubey

This paper proposes an observer-based framework for solving Partially Observable Markov Decision Processes (POMDPs) when an accurate model is not available. We first propose to use a Moving Horizon Estimation-Model Predictive Control…

系统与控制 · 电气工程与系统科学 2021-03-23 Hossein Nejatbakhsh Esfahani , Arash Bahari Kordabad , Sebastien Gros

Partially observable Markov decision processes (POMDPs) have recently become popular among many AI researchers because they serve as a natural model for planning under uncertainty. Value iteration is a well-known algorithm for finding…

人工智能 · 计算机科学 2011-06-02 N. L. Zhang , W. Zhang

Neural ordinary differential equations (ODEs) are widely recognized as the standard for modeling physical mechanisms, which help to perform approximate inference in unknown physical or biological environments. In partially observable (PO)…

机器学习 · 计算机科学 2023-10-31 Xuanle Zhao , Duzhen Zhang , Liyuan Han , Tielin Zhang , Bo Xu

We study finite memory belief approximation for partially observable (PO) stochastic optimal control (SOC) problems. While belief states are sufficient for SOC in partially observable Markov decision processes (POMDPs), they are generally…

系统与控制 · 电气工程与系统科学 2026-01-07 Mintae Kim

We study reinforcement learning with linear function approximation and finite-memory approximations for partially observed Markov decision processes (POMDPs). We first present an algorithm for the value evaluation of finite-memory feedback…

最优化与控制 · 数学 2025-05-22 Ali Devran Kara

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…

人工智能 · 计算机科学 2024-10-10 Guy Shani

We consider the problem of minimizing a certainty equivalent of the total or discounted cost over a finite and an infinite time horizon which is generated by a Partially Observable Markov Decision Process (POMDP). The certainty equivalent…

概率论 · 数学 2021-07-21 Nicole Bäuerle , Ulrich Rieder

This work compares ways of extending Reinforcement Learning algorithms to Partially Observed Markov Decision Processes (POMDPs) with options. One view of options is as temporally extended action, which can be realized as a memory that…

机器学习 · 计算机科学 2024-10-14 Shu Ishida , João F. Henriques