Using Reinforcement Learning to Herd a Robotic Swarm to a Target Distribution

Mathematics

• Reinforcement Learning 100%
• Swarm 95%
• Control Policy 54%
• Simulation Environment 14%
• Target 14%
• Q-learning 13%
• Mean-field Model 11%
• Grid Graph 10%
• Robot 10%
• Learning Algorithm 9%
• Control Strategy 9%
• Policy 8%
• Graph in graph theory 7%
• Simplify 7%
• Difference equation 7%
• Probability Distribution 6%
• Connected graph 6%
• Interaction 5%
• Observation 5%
• Vertex of a graph 4%
• Form 3%

Engineering & Materials Science

• Reinforcement learning 66%
• Difference equations 13%
• Probability distributions 10%
• Learning algorithms 9%
• Robots 7%