Two-Stage Reinforcement Learning Policy Search for Grid-Interactive Building Control

Engineering

• Reinforcement Learning 100%
• Learning Approach 33%
• Commercial Building 33%
• Model Building 33%
• Decision Time 33%
• Convex Optimization Problem 33%
• Local Optimum 33%
• Search Method 33%
• Optimal Policy 33%
• Policy Control 33%
• Solution Stage 33%
• Optimal Control 33%

Computer Science

• Reinforcement Learning 100%
• Predictive Model 66%
• Optimization Problem 33%
• Convex Optimization 33%
• High Performance Computing 33%
• Can Controller 33%
• Order Gradient 33%
• Solution Stage 33%
• Learning Approach 33%