Formalization of methods for the development of autonomous artificial intelligence systems

DOI10.1007/s10559-023-00612-zOpenAlexW4387429925MaRDI QIDQ6066037

L. B. Levenchuk, Michael Z. Zgurovsky, Pavlo O. Kasyanov

Publication date: 15 November 2023

Published in: Cybernetics and Systems Analysis (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s10559-023-00612-z

zbMATH Keywords

Markov decision processes\( \epsilon \)-optimal strategiesautonomous artificial intelligence system

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Berge's theorem for noncompact image sets
• Stochastic optimal control. The discrete time case
• Incomplete information in Markovian decision models
• The value iteration algorithm is not strongly polynomial for discounted dynamic programming
• Adaptive Markov control processes
• Continuity of equilibria for two-person zero-sum games with noncompact action sets and unbounded payoffs
• Reward is enough
• Average Cost Markov Decision Processes with Weakly Continuous Transition Probabilities
• Examples in Markov Decision Processes
• Algorithms for Reinforcement Learning
• The Statistical Research Group, 1942-1945
• Reduction of a Controlled Markov Model with Incomplete Data to a Problem with Complete Information in the Case of Borel State and Control Space
• The Optimal Control of Partially Observable Markov Processes over the Infinite Horizon: Discounted Costs
• Markov Decision Processes with Incomplete Information and Semiuniform Feller Transition Probabilities
• Decentralized Q-Learning for Stochastic Teams and Games
• Convergence of Finite Memory Q Learning for POMDPs and Near Optimality of Learned Policies Under Filter Stability

This page was built for publication: Formalization of methods for the development of autonomous artificial intelligence systems