JCEEES
Journal of Computer & Electrical and Electronics Engineering Sciences

JCEEES aims to publish original articles covering the theoretical foundations of major computer, electronic and electrical engineering sciences, as well as academic, commercial and educational aspects that propose new ideas for the application and design of artificial intelligence, software and information systems. In addition to wide-ranging regular topics, JCEEES also makes it a principle to include special topics covering specific topics in all areas of interest mainly in computational medicine, artificial intelligence, computer science, and electrical & electronic engineering science.

eISSN: 2980-177X
Creative Commons CC BY-NC-ND 4.0 International License.

Online Manuscript System

Index
Original Article
An imitation enhanced actor–critic approach for maze navigation
Abstract
Aims: This paper proposes a new method that integrates Imitation Learning (IL) into the Actor–Critic (AC) algorithm and evaluates its effect on the learning speed of agents in both obstacle and obstacle–free mazes.
Methods: The paper presents a new method that combines AC with a model of simply imitating observed behaviour, without direct internal access or inter–agent experience sharing. The proposed Imitation Enhanced Actor–Critic (IEAC) learning approach is evaluated through simulations on a maze pathfinding problem.
Results: Simulation results indicated that the proposed learning method significantly accelerated learning in terms of convergence speed and achieved higher stability compared to the standard Actor–Critic approach. In particular, agents using the imitation enhanced model reached optimal paths in fewer steps, in both mazes.
Conclusion: The findings demonstrate that integrating imitation learning into the actor–critic framework enhances convergence and stability, particularly in complex environments with obstacles. The proposed IEAC approach has potential applicability in autonomous navigation and robotic systems requiring efficient learning from observation.

Keywords : Social learning, reinforcement learning, multi–agent systems

Download Article


1. Argall, B. D., Chernova, S., Veloso, M., & Browning, B. (2009). A survey of robot learning from demonstration. Robotics and Autonomous Systems, 57(5), 469-483. https://doi.org/10.1016/j.robot.2008.10.024
2. Bentivegna, D., Cheng, G., & Atkeson, C. (2005). Learning from observation and from practice using behavioral primitives. Springer Tracts in Advanced Robotics, 15, 551-560. https://doi.org/10.1007/11008941_59
3. Block, A., Foster, D. J., Krishnamurthy, A., Simchowitz, M., & Zhang, C. (2024). Butterfly effects of SGD noise: Error amplification in behavior cloning and autoregression. Proceedings of the International Conference on Learning Representations (ICLR).
4. Bredeche, N., & Fontbonne, N. (2022). Social learning in swarm robotics. Philosophical Transactions of the Royal Society B: Biological Sciences, 377, 1843. https://doi.org/10.1098/rstb.2020.0309
5. Christianos, F., Schäfer, L., & Albrecht, S. V. (2021). Shared experience actor-critic for multi-agent reinforcement learning. Advances in Neural Information Processing Systems, 33, 10707-10717. http://arxiv.org/abs/2006.07169
6. Codevilla, F., Miiller, M., López, A., Koltun, V. & Dosovitskiy, A. (2018). End-to-end driving via conditional imitation learning. In 2018 IEEE International Conference on Robotics and Automation (ICRA). IEEE Press, 1-9. https://doi.org/10.1109/ICRA.2018.8460487
7. Erbas, M. D., Winfield, A. F., & Bull, L. (2014). Embodied imitation-enhanced reinforcement learning in multi-agent systems. Adaptive Behavior, 22(1), 31-50. https://doi.org/10.1177/1059712313500503
8. Guenter, F., & Billard, A. G. (2007). Using reinforcement learning to adapt an imitation task. IEEE International Conference on Intelligent Robots and Systems, 1022-1027. https://doi.org/10.1109/IROS.2007.4399449
9. Guo, X., Chang, S., Yu, M., Tesauro, G., & Campbell, M. (2019). Hybrid Reinforcement Learning with Expert State Sequences. Proceedings of the AAAI Conference on Artificial Intelligence, 33(01), 3739-3746. https://doi.org/10.1609/aaai.v33i01.33013739
10. Henrich, J. (2016). The Secret of Our Success: How Culture is Driving Human Evolution, Domesticating Our Species, and Making Us Smarter. Princeton University Press. https://doi.org/10.2307/j.ctvc77f0d
11. Mathewson, K. W., & Pilarski, P. M. (2017). Actor-critic reinforcement learning with simultaneous human control and feedback. arXiv. http://arxiv.org/abs/1703.01274
12. Ndousse, K., Eck, D., Levine, S., & Jaques, N. (2021). Emergent social learning via multi-agent reinforcement learning. arXiv. https://doi.org/10.48550/arXiv.2010.00581
13. Nguyen, S. M. (2024). The intrinsic motivation of reinforcement and imitation learning for sequential tasks. arXiv. https://doi.org/10.48550/arXiv.2412.20573
14. Rao, R. P. N., Shon, A. P., & Meltzoff, A. N. (2007). A Bayesian model of imitation in infants and robots. In C. L. Nehaniv & K. Dautenhahn (Eds), Imitation and Social Learning in Robots, Humans and Animals (1st ed., pp. 217-248). Cambridge University Press. https://doi.org/10.1017/CBO9780511489808.016
15. Sallab, A. El, Abdou, M., Perot, E., & Yogamani, S. (2017). Deep Reinforcement Learning framework for Autonomous Driving. Proceedings of the IS&T International Symposium on Electronic Imaging Science and Technology, 70-76. https://doi.org/10.2352/issn.2470-1173.2017.19.avm-023
16. Sharma, A., Kaur, H., & Prashar, D. (2023). Maze Solver: A Federated Reinforcement Learning Approach. 14th International Conference on Computing Communication and Networking Technologies (ICCCNT), pp.1-5. https://doi.org/10.1109/ICCCNT56998.2023.10307671
17. Sutton, R. S., & Barto, A. G. (2014). Reinforcement learning: an introduction (2nd ed.). MIT Press.
18. Uwano, F., Tatebe, N., Tajima, Y., Nakata, M., Kovacs, T., & Takadama, K. (2018). Multi-agent cooperation based on reinforcement learning with internal reward in maze problem. Journal of Control, Measurement, and System Integration, 11(4), 321-330. https://doi.org/10.9746/jcmsi.11.321
19. Yang, X., Gao, J., Wang, P., Long, W., & Fu, C. (2024). Social Learning with Actor-Critic for dynamic grasping of underwater robots via digital twins. Ocean Engineering, 306. https://doi.org/10.1016/j.oceaneng.2024.118070
Article available in :
Volume 4, Issue 2, 2026
Page : 64-71
https://doi.org/10.51271/JCEEES-0038
Article Information
Received : 27 Oca 2026
Accepted : 01 Nis 2026
Published : 13 Eki 2026
Corresponding Author :

Nurgül Kalaycı: Department of Software Engineering, Faculty of Engineering, Iğdır University, Iğdır, Turkiye

[email protected]
Citation : Kalaycı, N., & Erbaş, M. D. (2026). An imitation-enhanced actor-critic approach for maze navigation. J Comp Electr Electron Eng Sci, 4(2), 64-71. https://doi.org/10.51271/JCEEES-0038

Read: 1
Download : 6
Cited: 0
_Footer