Accuracy-Time Efficient Hyperparameter Optimization Using Actor-Critic-based Reinforcement Learning and Early Stopping in OpenAI Gym Environment.
Albert Budi ChristianChih-Yu LinYu-Chee TsengLan-Da VanWan-Hsun HuChia-Hsuan YuPublished in: IoTaIS (2022)
Keyphrases
- reinforcement learning
- actor critic
- early stopping
- function approximation
- optimal control
- reinforcement learning algorithms
- temporal difference
- learning algorithm
- approximate dynamic programming
- policy gradient
- state space
- machine learning
- dynamic programming
- multi agent
- convergence speed
- classification accuracy
- policy iteration
- training data