Robust adversarial reinforcement learning

Mathematics

• Reinforcement Learning 100%
• Training 70%
• Policy 48%
• Learning 45%
• Disturbance 31%
• Scenarios 30%
• Modeling Error 23%
• Simulation 21%
• Zero-sum 20%
• Optimal Policy 19%
• Baseline 18%
• Friction 16%
• Minimax 16%
• Neural Networks 15%
• Objective function 13%
• Experiment 12%
• Object 11%
• Demonstrate 9%
• Generalise 9%
• Generalization 8%

Engineering & Materials Science

• Reinforcement learning 66%
• Hoppers 28%
• Deep neural networks 21%
• Friction 15%
• Experiments 7%