Online shielding for reinforcement learning

Computer Science

• Reinforcement Learning 100%
• Markov Decision Process 40%
• Computation Time 20%
• Computer Game 20%
• Machine Learning Approach 20%
• Temporal Logic 20%
• Memory Consumption 20%
• Classical Computer 20%
• Large State Space 20%
• Learning Agent 20%

Chemical Engineering

• Reinforcement Learning 100%
• Learning System 20%

Engineering

• Markov Decision Process 40%
• Computer Game 20%