Learning and planning in partially observable environments without prior domain knowledge

DOI10.1016/J.IJAR.2021.12.004MaRDI QIDQ2076979zbMATH OpenOpenAlexFDO

Authors Yunlong Liu, Jianyang Zheng, Fangfang Chang

Publication date 22 February 2022

Published in International Journal of Approximate Reasoning (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.ijar.2021.12.004

zbMATH Keywords

Monte-Carlo tree searchplan under partial observabilitypredictive state representationsprior domain knowledge

Mathematics Subject Classification ID

Reasoning under uncertainty in the context of artificial intelligence (68T37)

Recommendations

• Efficient learning and planning with compressed predictive states
• Planning and acting in partially observable stochastic domains
• A Bayesian approach for learning and planning in partially observable Markov decision processes
• Learning partially observable non-deterministic action models
• scientific article; zbMATH DE number 5547961

Cites work

• A Bayesian approach for learning and planning in partially observable Markov decision processes
• A sparse sampling algorithm for near-optimal planning in large Markov decision processes
• Anytime point-based approximations for large POMDPS
• Bayesian reinforcement learning: a survey
• DESPOT: online POMDP planning with regularization
• scientific article; zbMATH DE number 1509479 (Why is no real title available?)
• scientific article; zbMATH DE number 2243398 (Why is no real title available?)
• Online planning algorithms for POMDPS
• Planning and acting in partially observable stochastic domains
• Robust Control of Markov Decision Processes with Uncertain Transition Matrices
• Scalable and efficient Bayes-adaptive reinforcement learning based on Monte-Carlo tree search
• Spectral learning of weighted automata. A forward-backward perspective

Cited in

(4)

• scientific article; zbMATH DE number 7368627 (Why is no real title available?)
• Classical Planning in Deep Latent Space
• Learning generalized policies from planning examples using concept languages
• Planning and acting in partially observable stochastic domains

Describes a project that uses

Uses Software

• POMDPS
• DESPOT

This page was built for publication: Learning and planning in partially observable environments without prior domain knowledge

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2076979)