Safe learning for near-optimal scheduling

DOI10.1007/978-3-030-85172-9_13zbMath1491.68151arXiv2005.09253OpenAlexW3196616774MaRDI QIDQ832074

Jean-François Raskin, Debraj Chakraborty, Damien Busatto-Gaston, Guillermo A. Pérez, Shibashis Guha

Publication date: 24 March 2022

Full work available at URL: https://arxiv.org/abs/2005.09253

zbMATH Keywords

task schedulingMonte-Carlo tree searchmodel-based learning

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Markov and semi-Markov decision processes (90C40) Problem solving in the context of artificial intelligence (heuristics, search strategies, etc.) (68T20)

Uses Software

• Storm
• Adam
• GitHub
• Baselines

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Continuity of the value of competitive Markov decision processes
• A sparse sampling algorithm for near-optimal planning in large Markov decision processes
• \({\mathcal Q}\)-learning
• Robustness of Structurally Equivalent Concurrent Parity Games
• Hard Real-Time Computing Systems
• A theory of the learnable
• Supervisory Control of a Class of Discrete Event Processes
• On the synthesis of strategies in infinite games
• Learning-Based Mean-Payoff Optimization in an Unknown MDP under Omega-Regular Constraints
• Stochastic games

This page was built for publication: Safe learning for near-optimal scheduling