Bottom-up learning of hierarchical models in a class of deterministic pomdp environments

DOI10.1515/AMCS-2015-0044zbMATH Open1322.90109OpenAlexW2296286269MaRDI QIDQ747543FDOQ747543

Authors: Hideaki Itoh, Hisao Fukumoto, Hiroshi Wakuya, Tatsuya Furukawa 

Publication date: 16 October 2015

Published in: International Journal of Applied Mathematics and Computer Science (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1515/amcs-2015-0044

Recommendations

• Dynamic hierarchical reinforcement learning based on the probability model
• Hierarchical Bayesian models of reinforcement learning: introduction and comparison to alternative methods
• Robustness to approximations and model learning in MDPs and POMDPs
• Recent advances in hierarchical reinforcement learning
• Recent advances in hierarchical reinforcement learning
• scientific article; zbMATH DE number 2086977

zbMATH Keywords

partially observable Markov decision processeshierarchical modelsbottom-up learning

Mathematics Subject Classification ID

Computational learning theory (68Q32) Markov and semi-Markov decision processes (90C40) Hierarchical systems (93A13)

Cites Work

• Title not available (Why is that?)
• Optimal control of Markov processes with incomplete state information
• Planning and acting in partially observable stochastic domains
• Title not available (Why is that?)
• Recent advances in hierarchical reinforcement learning
• Reliability modeling of fault tolerant control systems
• A Fast Learning Algorithm for Deep Belief Nets
• Planning with Markov decision processes. An AI perspective
• Title not available (Why is that?)
• Towards robotic assistants in nursing homes: Challenges and results
• The hierarchical hidden Markov model: Analysis and applications
• Transient and stationary characteristics of a packet buffer modelled as an \(\mathrm{MAP}/\mathrm{SM}/1/b\) system
• Semi-Markov-Based Approach for the Analysis of Open Tandem Networks with Blocking and Truncation
• Procedures for the Solution of a Finite-Horizon, Partially Observed, Semi-Markov Optimization Problem
• Multitime scale markov decision processes
• A Bayesian approach for learning and planning in partially observable Markov decision processes

Cited In (3)

• A new architecture for learning classifier systems to solve POMDP problems
• Learning to make predictions in partially observable environments without a generative model
• Hierarchies of probabilistic and team FIN-learning

Uses Software

• darch

This page was built for publication: Bottom-up learning of hierarchical models in a class of deterministic pomdp environments

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q747543)