Safe Reinforcement Learning with Probabilistic Guarantees Satisfying Temporal Logic Specifications in Continuous Action Spaces

Keyphrases

• Continuous Action Space 100%
• Probabilistic Guarantee 100%
• Safe Reinforcement Learning 100%
• Temporal Logic Specification 100%
• Controller 75%
• Probabilistic Safety Assessment 75%
• Reinforcement Learning 50%
• Safety Guarantee 50%
• Bounded Set 50%
• Control Input 50%
• System Behavior 25%
• Performance Improvement 25%
• Efficient Learning 25%
• Vanilla 25%
• Safety Verification 25%
• Reinforcement Learning Agent 25%
• Learning Procedure 25%
• Safety Performance 25%
• Safety Specification 25%
• Continuous State Space 25%
• Reinforcement Learning Approach 25%
• Dynamic Obstacles 25%

Computer Science

• Reinforcement Learning 100%
• Temporal Logic 100%
• Robotics 16%
• Complex Task 16%
• State Space 16%
• And-States 16%
• Learning Agent 16%
• System Behavior 16%
• Learning Approach 16%
• Performance Improvement 16%