Deep Reinforcement Learning with Adjustments
This addresses the problem of integrating RL into industries that prefer traditional control methods, offering an incremental improvement by combining their benefits.
The paper tackles the limited application of deep reinforcement learning (RL) in real-world physical systems by proposing a new Q-learning algorithm for continuous action spaces that bridges RL and traditional control, enabling easy adjustments for short-term requirements without retraining. The method and its approximation achieve both short-term and long-term goals without complex reward functions, as demonstrated in case studies.
Deep reinforcement learning (RL) algorithms can learn complex policies to optimize agent operation over time. RL algorithms have shown promising results in solving complicated problems in recent years. However, their application on real-world physical systems remains limited. Despite the advancements in RL algorithms, the industries often prefer traditional control strategies. Traditional methods are simple, computationally efficient and easy to adjust. In this paper, we first propose a new Q-learning algorithm for continuous action space, which can bridge the control and RL algorithms and bring us the best of both worlds. Our method can learn complex policies to achieve long-term goals and at the same time it can be easily adjusted to address short-term requirements without retraining. Next, we present an approximation of our algorithm which can be applied to address short-term requirements of any pre-trained RL algorithm. The case studies demonstrate that both our proposed method as well as its practical approximation can achieve short-term and long-term goals without complex reward functions.