Accuracy-Time Efficient Hyperparameter Optimization Using Actor-Critic-based Reinforcement Learning and Early Stopping in OpenAI Gym Environment

Mathematics

• Actors 92%
• Architecture 12%
• Classifier 12%
• Costs 16%
• Early Stopping 97%
• Experimental Results 11%
• Hyperparameters 83%
• Learning Algorithm 26%
• Machine Learning 24%
• Optimization 50%
• Random Forest 48%
• Reinforcement Learning 100%
• Standards 6%
• Support Vector 17%
• Valid 8%

Engineering & Materials Science

• Classifiers 15%
• Costs 16%
• Learning algorithms 36%
• Machine learning 32%
• Random forests 70%
• Reinforcement learning 66%