Online Model-free Safety Verification for Markov Decision Processes Without Safety Violation

Computer Science

• Markov Decision Process 100%
• State Space 50%
• Explicit Knowledge 50%
• Function Computation 50%
• Importance Sampling 50%
• Numerical Example 50%
• Function Value 50%
• Difference Method 50%
• temporal difference 50%

Engineering

• Markov Decision Process 100%
• Safety Verification 100%
• Safety Function 100%
• Numerical Example 33%
• Value Function 33%
• Policy Control 33%

Keyphrases

• Temporal Difference Learning 66%
• Value Function Estimation 33%