中文
相关论文

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

200 篇论文

Strategies for partially observable Markov decision processes (POMDP) typically require memory. One way to represent this memory is via automata. We present a method to learn an automaton representation of a strategy using a modification of…

人工智能 · 计算机科学 2024-10-03 Alexander Bork , Debraj Chakraborty , Kush Grover , Jan Kretinsky , Stefanie Mohr

This work introduces a novel deep learning-based architecture, termed the Deep Belief Markov Model (DBMM), which provides efficient, model-formulation agnostic inference in Partially Observable Markov Decision Process (POMDP) problems. The…

机器学习 · 计算机科学 2025-03-18 Giacomo Arcieri , Konstantinos G. Papakonstantinou , Daniel Straub , Eleni Chatzi

Many processes, such as discrete event systems in engineering or population dynamics in biology, evolve in discrete space and continuous time. We consider the problem of optimal decision making in such discrete state and action space…

机器学习 · 计算机科学 2020-10-27 Bastian Alt , Matthias Schultheis , Heinz Koeppl

Partially observable Markov decision processes (POMDPs) are standard models for dynamic systems with probabilistic and nondeterministic behaviour in uncertain environments. We prove that in POMDPs with long-run average objective, the…

计算机科学与博弈论 · 计算机科学 2022-09-29 Krishnendu Chatterjee , Raimundo Saona , Bruno Ziliotto

Partially-Observable Markov Decision Processes (POMDPs) are a well-known stochastic model for sequential decision making under limited information. We consider the EXPTIME-hard problem of synthesising policies that almost-surely reach some…

人工智能 · 计算机科学 2021-03-22 Sebastian Junges , Nils Jansen , Sanjit A. Seshia

We consider finite model approximations of discrete-time partially observed Markov decision processes (POMDPs) under the discounted cost criterion. After converting the original partially observed stochastic control problem to a fully…

系统与控制 · 计算机科学 2017-10-20 Naci Saldi , Serdar Yüksel , Tamás Linder

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…

人工智能 · 计算机科学 2013-01-14 Pascal Poupart , Luis E. Ortiz , Craig Boutilier

Much of reinforcement learning theory is built on top of oracles that are computationally hard to implement. Specifically for learning near-optimal policies in Partially Observable Markov Decision Processes (POMDPs), existing algorithms…

机器学习 · 计算机科学 2022-06-08 Noah Golowich , Ankur Moitra , Dhruv Rohatgi

We consider the problem belief-state monitoring for the purposes of implementing a policy for a partially-observable Markov decision process (POMDP), specifically how one might approximate the belief state. Other schemes for belief-state…

人工智能 · 计算机科学 2013-01-18 Pascal Poupart , Craig Boutilier

The continuous nature of belief states in POMDPs presents significant computational challenges in learning the optimal policy. In this paper, we consider an approach that solves a Partially Observable Reinforcement Learning (PORL) problem…

机器学习 · 计算机科学 2025-10-15 Ameya Anjarlekar , Rasoul Etesami , R Srikant

The objective is to study an on-line Hidden Markov model (HMM) estimation-based Q-learning algorithm for partially observable Markov decision process (POMDP) on finite state and action sets. When the full state observation is available,…

机器学习 · 计算机科学 2018-09-25 Hyung-Jin Yoon , Donghwan Lee , Naira Hovakimyan

Optimal decision-making presents a significant challenge for autonomous systems operating in uncertain, stochastic and time-varying environments. Environmental variability over time can significantly impact the system's optimal decision…

机器人学 · 计算机科学 2024-03-11 Gokul Puthumanaillam , Xiangyu Liu , Negar Mehr , Melkior Ornik

Partially Observable Markov Decision Processes (POMDPs) can model complex sequential decision-making problems under stochastic and uncertain environments. A main reason hindering their broad adoption in real-world applications is the lack…

We consider the problem of imitation learning from expert demonstrations in partially observable Markov decision processes (POMDPs). Belief representations, which characterize the distribution over the latent states in a POMDP, have been…

机器学习 · 计算机科学 2019-06-25 Tanmay Gangwani , Joel Lehman , Qiang Liu , Jian Peng

Partial observability is a common challenge in many reinforcement learning applications, which requires an agent to maintain memory, infer latent states, and integrate this past information into exploration. This challenge leads to a number…

机器学习 · 计算机科学 2020-10-27 Chi Jin , Sham M. Kakade , Akshay Krishnamurthy , Qinghua Liu

Addressing uncertainty is critical for autonomous systems to robustly adapt to the real world. We formulate the problem of model uncertainty as a continuous Bayes-Adaptive Markov Decision Process (BAMDP), where an agent maintains a…

机器人学 · 计算机科学 2019-05-09 Gilwoo Lee , Brian Hou , Aditya Mandalika , Jeongseok Lee , Sanjiban Choudhury , Siddhartha S. Srinivasa

In this paper we study online Reinforcement Learning (RL) in partially observable dynamical systems. We focus on the Predictive State Representations (PSRs) model, which is an expressive model that captures other well-known models such as…

机器学习 · 计算机科学 2022-08-16 Wenhao Zhan , Masatoshi Uehara , Wen Sun , Jason D. Lee

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…

人工智能 · 计算机科学 2024-03-01 Daniele Meli , Alberto Castellini , Alessandro Farinelli

This paper investigates manipulation of multiple unknown objects in a crowded environment. Because of incomplete knowledge due to unknown objects and occlusions in visual observations, object observations are imperfect and action success is…

机器人学 · 计算机科学 2014-07-09 Joni Pajarinen , Ville Kyrki

Real-world planning problems, including autonomous driving and sustainable energy applications like carbon storage and resource exploration, have recently been modeled as partially observable Markov decision processes (POMDPs) and solved…

人工智能 · 计算机科学 2024-08-01 Robert J. Moss , Anthony Corso , Jef Caers , Mykel J. Kochenderfer