PAC-Bayes control: learning policies that provably generalize to novel environments

Computer Science

• Neural Network 100%
• Machine Learning 33%
• Optimization Problem 33%
• And-States 33%
• Learning Algorithm 33%
• Stochastic Control 33%
• Supervised Learning 33%
• Convex Optimization 33%
• Gradient Descent 33%
• Relative Entropy 33%
• Robot 33%
• Obstacle Avoidance 33%

Keyphrases

• Relative Entropy Programming 25%
• Obstacle Environment 25%
• Parameterized Policy 25%