中文
相关论文

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

200 篇论文

The partially observable Markov decision process (POMDP) provides a principled general model for planning under uncertainty. However, solving a general POMDP is computationally intractable in the worst case. This paper introduces…

人工智能 · 计算机科学 2016-02-24 Min Chen , Emilio Frazzoli , David Hsu , Wee Sun Lee

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…

机器学习 · 计算机科学 2026-04-02 Philip Jordan , Maryam Kamgarpour

In this study I proposed a filtering beliefs method for improving performance of Partially Observable Markov Decision Processes(POMDPs), which is a method wildly used in autonomous robot and many other domains concerning control policy. My…

人工智能 · 计算机科学 2021-01-07 Oscar LiJen Hsu

Partially Observable Markov Decision Processes (POMDPs) remain a core challenge in reinforcement learning due to incomplete state information. We address this by reformulating POMDPs as fully observable processes with fixed-length…

机器学习 · 计算机科学 2025-09-16 Wuhao Wang , Zhiyong Chen

This paper proposes Partially Observable Reference Policy Programming, a novel anytime online approximate POMDP solver which samples meaningful future histories very deeply while simultaneously forcing a gradual policy update. We provide…

人工智能 · 计算机科学 2025-07-17 Edward Kim , Hanna Kurniawati

Possibilistic and qualitative POMDPs (pi-POMDPs) are counterparts of POMDPs used to model situations where the agent's initial belief or observation probabilities are imprecise due to lack of past experiences or insufficient data…

人工智能 · 计算机科学 2013-09-27 Nicolas Drougard , Florent Teichteil-Konigsbuch , Jean-Loup Farges , Didier Dubois

We are interested in enabling autonomous agents to learn and reason about systems with hidden states, such as locking mechanisms. We cast this problem as learning the parameters of a discrete Partially Observable Markov Decision Process…

机器学习 · 计算机科学 2026-02-04 Seiji Shaw , Travis Manderson , Chad Kessens , Nicholas Roy

The agent learns to organize decision behavior to achieve a behavioral goal, such as reward maximization, and reinforcement learning is often used for this optimization. Learning an optimal behavioral strategy is difficult under the…

机器学习 · 计算机科学 2023-05-09 Kazuki Takahashi , Tomoki Fukai , Yutaka Sakai , Takashi Takekawa

We study reinforcement learning with function approximation for large-scale Partially Observable Markov Decision Processes (POMDPs) where the state space and observation space are large or even continuous. Particularly, we consider Hilbert…

机器学习 · 计算机科学 2022-06-27 Masatoshi Uehara , Ayush Sekhari , Jason D. Lee , Nathan Kallus , Wen Sun

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…

人工智能 · 计算机科学 2011-06-02 M. Hauskrecht

We study an approximation method for partially observed Markov decision processes (POMDPs) with continuous spaces. Belief MDP reduction, which has been the standard approach to study POMDPs requires rigorous approximation methods for…

最优化与控制 · 数学 2025-01-20 Ali Devran Kara , Erhan Bayraktar , Serdar Yuksel

In many practical settings control decisions must be made under partial/imperfect information about the evolution of a relevant state variable. Partially Observable Markov Decision Processes (POMDPs) is a relatively well-developed framework…

机器学习 · 计算机科学 2021-12-30 Yanling Chang , Alfredo Garcia , Zhide Wang , Lu Sun

In real-world scenarios, the observation data for reinforcement learning with continuous control is commonly noisy and part of it may be dynamically missing over time, which violates the assumption of many current methods developed for…

机器学习 · 计算机科学 2019-02-18 Yuhui Wang , Hao He , Xiaoyang Tan

We study observation-based strategies for partially-observable Markov decision processes (POMDPs) with omega-regular objectives. An observation-based strategy relies on partial information about the history of a play, namely, on the past…

计算机科学中的逻辑 · 计算机科学 2015-05-14 Krishnendu Chatterjee , Laurent Doyen , Thomas A. Henzinger

Autonomous systems are often required to operate in partially observable environments. They must reliably execute a specified objective even with incomplete information about the state of the environment. We propose a methodology to…

人工智能 · 计算机科学 2020-01-14 Maxime Bouton , Jana Tumova , Mykel J. Kochenderfer

In applications of offline reinforcement learning to observational data, such as in healthcare or education, a general concern is that observed actions might be affected by unobserved factors, inducing confounding and biasing estimates…

机器学习 · 计算机科学 2023-03-24 Andrew Bennett , Nathan Kallus

Partially Observable Markov Decision Processes (POMDPs) provide a robust framework for decision-making under uncertainty in applications such as autonomous driving and robotic exploration. Their extension, $\rho$POMDPs, introduces…

人工智能 · 计算机科学 2025-02-05 Ron Benchetrit , Idan Lev-Yehudi , Andrey Zhitnikov , Vadim Indelman

In this paper, we expand the Bayesian persuasion framework to account for unobserved confounding variables in sender-receiver interactions. While traditional models assume that belief updates follow Bayesian principles, real-world scenarios…

人工智能 · 计算机科学 2025-08-11 Nishanth Venkatesh S. , Heeseung Bang , Andreas A. Malikopoulos

In real-world reinforcement learning (RL) scenarios, agents often encounter partial observability, where incomplete or noisy information obscures the true state of the environment. Partially Observable Markov Decision Processes (POMDPs) are…

机器学习 · 计算机科学 2025-05-19 Ashok Arora , Neetesh Kumar

Partially observable Markov decision processes (POMDPs) form a prominent model for uncertainty in sequential decision making. We are interested in constructing algorithms with theoretical guarantees to determine whether the agent has a…