A Comprehensive Evaluation and Comparison of Enhanced Learning Methods

Jintong Song; Houze Liu; Keqin Li; Jingxiao Tian; Yuhong Mo

doi:10.54097/8c4zvn35

Authors

Jintong Song
Houze Liu
Keqin Li
Jingxiao Tian
Yuhong Mo

DOI:

https://doi.org/10.54097/8c4zvn35

Keywords:

Reinforcement learning, method comparison, advantages and disadvantages analysis.

Abstract

This paper provides a comprehensive evaluation and comparison of current reinforcement learning methods. By analyzing the strengths and weaknesses of the main methods, such as value function-based, strategy gradient-based, and value and strategy-based methods, the differences in their performances on standard problems and the applicable scenarios are explored. Meanwhile, other methods such as Monte Carlo Tree Search (MCTS) and evolutionary methods are also briefly introduced. Through the research and analysis in this paper, it provides reference and guidance for choosing appropriate reinforcement learning methods, and promotes the development and application of reinforcement learning techniques in practical applications.

Downloads

Download data is not yet available.

References

Y.-T. Hsieh, Z. Qi, and D. Pompili, "ML-based Joint Doppler Estimation and Compensation in Underwater Acoustic Communications," in Proceedings of the 16th International Conference on Underwater Networks & Systems (WUWNet '22), New York, NY, USA, 2022, pp. 1–8.

Z. Li, Y. Huang, M. Zhu, J. Zhang, J. Chang, and H. Liu, “Feature Manipulation for DDPM based Change Detection,” arXiv.org, Mar. 23, 2024.

Y. Lai, Z. Luo, and Z. Yu, "Detect Any Deepfakes: Segment Anything Meets Face Forgery Detection and Localization," in Biometric Recognition, W. Jia, Ed., vol. 14463, Lecture Notes in Computer Science, Springer, Singapore, 2023.

Q. Cheng et al., “Secure Digital Asset Transactions: Integrating Distributed Ledger Technology with Safe AI Mechanisms”, AJST, vol. 9, no. 3, pp. 156–161, Mar. 2024.

S. Zhao et al., “Defending Against Weight-Poisoning Backdoor Attacks for Parameter-Efficient Fine-Tuning,” arXiv.org, Mar. 29, 2024.

J. Tian et al., "LESSON: Multi-Label Adversarial False Data Injection Attack for Deep Learning Locational Detection," in IEEE Transactions on Dependable and Secure Computing.

Xiaotian Zhang,Yawen Wang,Zhiqing Xie et al. Reinforcement Learning Approach for Sequence Determination of Class Integration Tests [J]. Computer Engineering, 2024, 50 (01): 68-78.

Rongyun Li. Reinforcement Learning Approach for Game Manipulation Behavior Imitation [D]. University of Electronic Science and Technology, 2022.

Yin Hang. Epistemic modeling of self-reinforcement learning methods based on deep residual networks[D]. Liaoning University of Engineering and Technology, 2022.

Wei Minatong. Deep network-based video repair and reinforcement learning methods in unstable environments[D]. University of Science and Technology of China, 2021.

Zhang Wei. Deep reinforcement learning for target localization and recognition[D]. Xi'an University of Technology, 2021.

Lei Xu. Deep Reinforcement Learning for Text Games[D]. Heilongjiang University, 2021.