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

DOI10.1515/amcs-2015-0044zbMath1322.90109OpenAlexW2296286269MaRDI QIDQ747543

Hisao Fukumoto, Tatsuya Furukawa, Hiroshi Wakuya, Hideaki Itoh

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

zbMATH Keywords

hierarchical modelspartially observable Markov decision processesbottom-up learning

Mathematics Subject Classification ID

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

Uses Software

• darch

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Planning and acting in partially observable stochastic domains
• 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
• Optimal control of Markov processes with incomplete state information
• Planning with Markov Decision Processes: An AI Perspective
• Reliability Modeling of Fault Tolerant Control Systems
• 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
• Towards robotic assistants in nursing homes: Challenges and results
• Multitime scale markov decision processes
• A Fast Learning Algorithm for Deep Belief Nets
• Recent advances in hierarchical reinforcement learning