Deceptive Reinforcement Learning Under Adversarial Manipulations on Cost Signals

Mathematics

• Reinforcement Learning 100%
• Manipulation 69%
• Costs 48%
• Q-learning 44%
• Policy 39%
• Attack 27%
• Learning 24%
• Vulnerability 17%
• Learning Algorithm 15%
• Hazard 14%
• Water 13%
• Control System 11%
• Converge 8%
• Framework 7%

Engineering & Materials Science

• Reinforcement learning 66%
• Costs 25%
• Hazards 11%
• Learning algorithms 11%
• Control systems 8%