Totally model-free actor-critic recurrent neural-network reinforcement learning in non-Markovian domains

DOI10.1007/s10479-016-2366-2zbMath1423.68386OpenAlexW2549405740MaRDI QIDQ1699932

Eiji Mizutani, Stuart E. Dreyfus

Publication date: 26 February 2018

Published in: Annals of Operations Research (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s10479-016-2366-2

zbMATH Keywords

recurrent neural networksactor-critic reinforcement learningnon-Markovian dependencies

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Neural networks for/in biological studies, artificial life and related topics (92B20)

Related Items (2)

Designing an efficient blood supply chain network in crisis: neural learning, optimization and case study ⋮ Totally model-free actor-critic recurrent neural-network reinforcement learning in non-Markovian domains

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Reinforcement learning in the brain
• The art and theory of dynamic programming
• Totally model-free actor-critic recurrent neural-network reinforcement learning in non-Markovian domains
• \({\mathcal Q}\)-learning
• Reinforcement learning of non-Markov decision processes
• Scalable and Efficient Bayes-Adaptive Reinforcement Learning Based on Monte-Carlo Tree Search
• Absolute stability of global pattern formation and parallel memory storage by competitive neural networks
• Functional Approximations and Dynamic Programming
• OnActor-Critic Algorithms
• Simulation-based optimization of Markov reward processes
• Punish/Reward: Learning with a Critic in Adaptive Threshold Systems

This page was built for publication: Totally model-free actor-critic recurrent neural-network reinforcement learning in non-Markovian domains