Abstract
Several complex sequential decision-making problems have been successfully implemented using reinforcement learning (RL) for continuous optimal control. However, the sample efficiency of data collection process during the learning phase is still not well addressed. The convergence rate to the optimal policy as well as the time of the learning process are strongly influenced by the efficiency of the data collected by the agent during the learning phase. This paper proposes a method to generate efficient sample data which allows the agent to collect high reward trajectories more frequently, decreasing the learning phase time. The proposed method consists of Complementary reward (CR) function augmented to the traditional reward function. The CR tends to infinity when the control input leads to the system performance that meets the given requirements very accurately. Consequently, the control policy which maximizes the reward function can render the system to optimal performance. The main contributions of this study include the following aspects: (1) a new proposed Complementary reward that is augmented to the reward function which improves performance of the reinforcement learning based controller in terms of system requirements; (2) speed-up of training phase via generation of more efficient data resulting in a better learned policy.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Timothy, P., Lillicrap, et al.: Continuous control with deep reinforcement learning (2015). https://doi.org/10.48550/ARXIV.1509.02971
Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. Adaptive Computation And Machine Learning Series, 2nd edn. The MIT Press, Cambridge, Massachusetts (2018). ISBN: 9780262039246
Long Vu, T. et al.: Barrier Function-based Safe Reinforcement Learning for Emergency Control of Power Systems (2021). https://doi.org/10.48550/ARXIV.2103.14186
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Andrei, G.C., Jha, M.S., Theillol, D. (2023). Complementary Reward Function Based Learning Enhancement for Deep Reinforcement Learning. In: Theilliol, D., Korbicz, J., Kacprzyk, J. (eds) Recent Developments in Model-Based and Data-Driven Methods for Advanced Control and Diagnosis. ACD 2022. Studies in Systems, Decision and Control, vol 467. Springer, Cham. https://doi.org/10.1007/978-3-031-27540-1_21
Download citation
DOI: https://doi.org/10.1007/978-3-031-27540-1_21
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-27539-5
Online ISBN: 978-3-031-27540-1
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)