Core Concepts
Novel method for imitation learning using Signal Temporal Logic to train neural networks to imitate complex controllers efficiently.
Stats
"The simulation time is 15 seconds."
"Parameters α = 0.2 and β = 0.2 are used in the dynamics of the flying robot."
"Neural network has RELU as activation functions, 6 hidden layers, and one output layer."
Quotes
"We propose a simple grid-based method to construct ε-nets satisfying a separation requirement."
"The dataset aggregation algorithm determines whether it should generate new data for retraining or stop."