Planning and learning in partially observable systems via filter stability

DOI10.1145/3564246.3585099MaRDI QIDQ6499234

Noah Golowich, Dhruv Rohatgi, Ankur Moitra

Publication date: 8 May 2024

zbMATH Keywords

partially observable Markov decision processesfilter stability

Mathematics Subject Classification ID

Theory of computing (68Qxx)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Planning and acting in partially observable stochastic domains
• Observability and nonlinear filtering
• Robust recursive estimation in the presence of heavy-tailed observation noise
• On the complexity of partially observed Markov decision processes
• Exponential stability for nonlinear filtering
• Smoothed analysis for tensor methods in unsupervised learning
• Exponential filter stability via Dobrushin's coefficient
• Uniform observability of hidden Markov models and filter stability for unstable signals
• Exponential stability of filters and smoothers for hidden Markov models
• Tensor decompositions for learning latent variable models
• DESPOT: Online POMDP Planning with Regularization
• Peak-to-Average Power Ratio of Good Codes for Gaussian Channel
• Lyapunov Exponents for Finite State Nonlinear Filtering
• Settling the complexity of computing two-player Nash equilibria
• Multiagent Systems
• The Complexity of Markov Decision Processes
• Coping with singular transition matrices in estimation and control stability theory†
• Superhuman AI for heads-up no-limit poker: Libratus beats top professionals
• The Complexity of Computing a Nash Equilibrium
• Smoothed analysis of tensor decompositions
• Stochastic Games
• Using mixture models for collaborative filtering
• On the complexity of \(k\)-SAT

This page was built for publication: Planning and learning in partially observable systems via filter stability