On reinforcement memory for non-Markovian control

DOI10.1007/978-0-85729-130-1_13zbMATH Open1208.93068OpenAlexW1535225803MaRDI QIDQ3076950FDOQ3076950

Authors: Hassab Elgawi Osman 

Publication date: 25 February 2011

Published in: Research and Development in Intelligent Systems XXVII (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/978-0-85729-130-1_13

Recommendations

• Reinforcement learning of non-Markov decision processes
• Robust reinforcement learning control with static and dynamic stability
• Non-parametric policy search with limited information loss
• Totally model-free actor-critic recurrent neural-network reinforcement learning in non-Markovian domains
• Autonomous reinforcement learning with experience replay

zbMATH Keywords

actor-critic (AC)non-Markovian reinforcement tasksrobotic memory controller

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40) Automated systems (robots, etc.) in control theory (93C85)

Cited In (4)

• Title not available (Why is that?)
• Title not available (Why is that?)
• Totally model-free actor-critic recurrent neural-network reinforcement learning in non-Markovian domains
• Reinforcement learning in non-Markovian environments

This page was built for publication: On reinforcement memory for non-Markovian control

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3076950)