Q-Learning for robust satisfaction of signal temporal logic specifications

Mathematics

• Q-learning 100%
• Temporal Logic 71%
• Specification 53%
• Logic Synthesis 25%
• Robustness 25%
• Performance Bounds 21%
• Unknown 19%
• Markov Decision Process 18%
• Stochastic Dynamics 17%
• Optimal Policy 17%
• Transition Probability 15%
• Resolve 14%
• Policy 14%
• Learning 13%
• Synthesis 13%
• Semantics 12%
• Partition 11%
• Simulation 9%
• Performance 8%
• Standards 8%
• Approximation 7%
• Form 6%

Engineering & Materials Science

• Temporal logic 70%
• Specifications 38%
• Logic Synthesis 20%
• Markov processes 15%
• Semantics 10%

Business & Economics

• Logic 45%
• Stochastic Dynamics 18%
• Transition Probability 17%
• Markov Decision Process 17%
• Optimal Policy 14%
• Approximation 12%
• Performance 11%
• Simulation 10%