English
Related papers

Related papers: Policy Iteration for Factored MDPs

200 papers

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

Randomized value functions offer a promising approach towards the challenge of efficient exploration in complex environments with high dimensional state and action spaces. Unlike traditional point estimate methods, randomized value…

Machine Learning · Computer Science 2019-07-02 Ahmed Touati , Harsh Satija , Joshua Romoff , Joelle Pineau , Pascal Vincent

Regularized MDPs serve as a smooth version of original MDPs. However, biased optimal policy always exists for regularized MDPs. Instead of making the coefficient{\lambda}of regularized term sufficiently small, we propose an adaptive…

Machine Learning · Computer Science 2020-11-03 Wenhao Yang , Xiang Li , Guangzeng Xie , Zhihua Zhang

We introduce and study constrained Markov Decision Processes (cMDPs) with anytime constraints. An anytime constraint requires the agent to never violate its budget at any point in time, almost surely. Although Markovian policies are no…

Machine Learning · Computer Science 2024-06-14 Jeremy McMahan , Xiaojin Zhu

Hybrid Bayesian networks (HBN) contain complex conditional probabilistic distributions (CPD) specified as partitioned expressions over discrete and continuous variables. The size of these CPDs grows exponentially with the number of parent…

Artificial Intelligence · Computer Science 2024-02-26 Peng Lin , Martin Neil , Norman Fenton

We consider local planning in fixed-horizon MDPs with a generative model under the assumption that the optimal value function lies close to the span of a feature map. The generative model provides a local access to the MDP: The planner can…

Machine Learning · Computer Science 2021-07-12 Gellért Weisz , Philip Amortila , Barnabás Janzer , Yasin Abbasi-Yadkori , Nan Jiang , Csaba Szepesvári

This paper describes valuation-based systems for representing and solving discrete optimization problems. In valuation-based systems, we represent information in an optimization problem using variables, sample spaces of variables, a set of…

Artificial Intelligence · Computer Science 2013-04-05 Prakash P. Shenoy , Glenn Shafer

We introduce a new approximate solution technique for first-order Markov decision processes (FOMDPs). Representing the value function linearly w.r.t. a set of first-order basis functions, we compute suitable weights by casting the…

Artificial Intelligence · Computer Science 2012-07-09 Scott Sanner , Craig Boutilier

Model checking undiscounted reachability and expected-reward properties on Markov decision processes (MDPs) is key for the verification of systems that act under uncertainty. Popular algorithms are policy iteration and variants of value…

Logic in Computer Science · Computer Science 2023-01-25 Arnd Hartmanns , Sebastian Junges , Tim Quatmann , Maximilian Weininger

In centralized multi-agent systems, often modeled as multi-agent partially observable Markov decision processes (MPOMDPs), the action and observation spaces grow exponentially with the number of agents, making the value and belief…

Artificial Intelligence · Computer Science 2024-02-26 Maris F. L. Galesloot , Thiago D. Simão , Sebastian Junges , Nils Jansen

This paper aims to build a probabilistic framework for Howard's policy iteration algorithm using the language of forward-backward stochastic differential equations (FBSDEs). As opposed to conventional formulations based on partial…

Optimization and Control · Mathematics 2024-10-28 Yutian Wang , Yuan-Hua Ni , Zengqiang Chen , Ji-Feng Zhang

Factorization machines (FMs) are a powerful tool for regression and classification in the context of sparse observations, that has been successfully applied to collaborative filtering, especially when side information over users or items is…

Machine Learning · Computer Science 2022-12-21 Jill-Jênn Vie , Tomas Rigaux , Hisashi Kashima

In this article, variational state estimation is examined from the dynamic programming perspective. This leads to two different value functional recursions depending on whether backward or forward dynamic programming is employed. The result…

Methodology · Statistics 2025-12-17 Filip Tronarp

Non-negative matrix factorization (NMF) is one of the most popular decomposition techniques for multivariate data. NMF is a core method for many machine-learning related computational problems, such as data compression, feature extraction,…

Numerical Analysis · Computer Science 2017-12-07 Gabriele Torre , Michael Graber

Tensors are ubiquitous in science and engineering and tensor factorization approaches have become important tools for the characterization of higher order structure. Factorizations includes the outer-product rank Canonical Polyadic…

Machine Learning · Statistics 2023-10-05 Jesper Løve Hinrich , Morten Mørup

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

Existing value function approximation methods have been successfully used in many applications, but they often lack useful a priori error bounds. We propose a new approximate bilinear programming formulation of value function approximation,…

Artificial Intelligence · Computer Science 2010-06-15 Marek Petrik , Shlomo Zilberstein

Policy gradient methods have had great success in solving continuous control tasks, yet the stochastic nature of such problems makes deterministic value estimation difficult. We propose an approach which instead estimates a distribution by…

Machine Learning · Computer Science 2017-12-07 Peter Henderson , Thang Doan , Riashat Islam , David Meger

We propose a novel value function approximation technique for Markov decision processes. We consider the problem of compactly representing the state-action value function using a low-rank and sparse matrix model. The problem is to decompose…

Machine Learning · Computer Science 2015-09-02 Hao Yi Ong

Robust Markov decision processes (r-MDPs) extend MDPs by explicitly modelling epistemic uncertainty about transition dynamics. Learning r-MDPs from interactions with an unknown environment enables the synthesis of robust policies with…

Machine Learning · Computer Science 2025-11-21 Yannik Schnitzer , Alessandro Abate , David Parker
‹ Prev 1 4 5 6 7 8 10 Next ›