Jun Lai

Jun Lai


Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
6 December 2022 in Entropy
Verified
Journal Article
Open access
PDF file
ZLZeyang Lin
Zeyang Lin
JLJun Lai
Jun Lai
XCXiliang Chen
Xiliang Chen
LCLei Cao
Lei Cao
JWJun Wang
Jun Wang
With the continuous development of deep reinforcement learning in intelligent control, combining automatic curriculum learning and deep reinforcement learning can improve the training performance and efficiency of algorithms from easy to difficult. Most existing automatic curriculum learning algorithms perform curriculum ranking through expert experience and a single network, which has the problems of difficult curriculum task ranking and slow convergence speed. In this paper, we propose a curriculum reinforcement learning method based on K-Fold Cross Validation that can estimate the relativity score of task curriculum difficulty. Drawing lessons from the human concept of curriculum learning from easy to difficult, this method divides automatic curriculum learning into a curriculum difficulty assessment stage and a curriculum sorting stage. Through parallel training of the teacher model and cross-evaluation of task sample difficulty, the method can better sequence curriculum learning tasks. Finally, simulation comparison experiments were carried out in two types of multi-agent experimental environments. The experimental results show that the automatic curriculum learning method based on K-Fold cross-validation can improve the training speed of the MADDPG algorithm, and at the same time has a certain generality for multi-agent deep reinforcement learning algorithm based on the replay buffer mechanism.

20 July 2022 in Mathematics
Verified
Journal Article
Open access
PDF file
ZLZeyang Lin
Zeyang Lin
JLJun Lai
Jun Lai
XCXiliang Chen
Xiliang Chen
LCLei Cao
Lei Cao
JWJun Wang
Jun Wang
In recent years, reinforcement learning algorithms based on automatic curriculum learning have been increasingly applied to multi-agent system problems. However, in the sparse reward environment, the reinforcement learning agents get almost no feedback from the environment during the whole training process, which leads to a decrease in the convergence speed and learning efficiency of the curriculum reinforcement learning algorithm. Based on the automatic curriculum learning algorithm, this paper proposes a curriculum reinforcement learning method based on the curiosity model (CMCL). The method divides the curriculum sorting criteria into temporal-difference error and curiosity reward, uses the K-fold cross validation method to evaluate the difficulty priority of task samples, uses the Intrinsic Curiosity Module (ICM) to evaluate the curiosity priority of the task samples, and uses the curriculum factor to adjust the learning probability of the task samples. This study compares the CMCL algorithm with other baseline algorithms in cooperative-competitive environments, and the experimental simulation results show that the CMCL method can improve the training performance and robustness of multi-agent deep reinforcement learning algorithms.

27 December 2025 in Fractal and Fractional
Verified
Journal Article
Open access
PDF file
KLKunyuan Li
Kunyuan Li
XZXiongwei Zhang
Xiongwei Zhang
KYKui Yao
Kui Yao
JLJun Lai
Jun Lai
MSMeng Sun
Meng Sun
WYWang Yangjun
Wang Yangjun
This paper uses the theory of self-affine fractal functions to model the dynamic flight graphs of starling flocks, integrating the fractional calculus of self-affine fractal functions to quantitatively characterize the intrinsic nonlinear dynamics and memory effects within the system, employing statistical inference methods to find the fractal fit for the images. The changes in box dimensions over time could characterize the phase transition process of the starling flight flocks. By analyzing the rate of change of fractal dimensions, we identify critical points corresponding to phase transitions during collective flight behavior. During the flight of the starling flocks, a real-time phase transition process for evading attacks and effective advancement has been identified. Experimental data confirms the effectiveness of controlling the phase transition.