• e - ISSN No : 2832-4277
Submit Paper
IJRTTE Logo

INTERNATIONAL JOURNAL OF RECENT TRENDS IN TECHNOLOGY AND ENGINEERING (IJRTTE)

Home / Archives / Vol. 1 No. 3 / Articles

Deep Reinforcement Learning for Intelligent and Autonomous Game Agents

R Venkatasubramanian
Professor, Department of EEE, New Prince Shri Bhavani College of Engineering and Technology, India.
Varalakshmi Dandu
Assistant Professor, Selection Grade, School of Management, Presidency University, India
P Balakrishnan
Professor, Department of Electrical and Electronics Engineering, J.J. College of Engineering and Technology, India.

Keywords: Deep Reinforcement Learning, Autonomous Game Agents, Intelligent Decision Making, Multi-Agent Systems, Policy Optimization, Game AI

Abstract

The rapid evolution of game environments demands intelligent agents capable of autonomous and adaptive decision-making. This paper presents a deep reinforcement learning (DRL) framework for designing intelligent game agents that operate in dynamic, complex, and partially observable environments. Leveraging the advantages of state-of-the art DRL algorithms such as Deep Q-Networks (DQN), Proximal Policy Optimization (PPO), and Soft Actor-Critic (SAC) the proposed approach enables agents to learn optimal strategies through environment interaction without the need for explicit programming or predefined rules. In contrast with conventional rule-based/heuristic approaches, the framework encourages generalization between distinct game setting, enables scalable multi-agent coordination, and incorporates reward-shaping techniques speeding up convergence. To overcome some of the shortcomings of these approaches including lack of relevance to scenario-specific tasks, limited scalability, and a lack of interpretability, our model is designed to feature modular training pipelines with an optional explain ability component derived from attention-based layers and SHAP analysis, in an online streaming manner. Experimental results on different game simulation show that our system outperforms baselines in adaptability, strategy generation, and self-learning. This paper introduces a powerful and flexible DRL-based framework for training future autonomous game agents, which may have applications outside of games, e.g., robotics, digital twin systems, and simulating-based training environment.
PDF
Download Certificate
Details
Published
2022-09-29
Pages
1-10
Issue
Vol. 1 No. 3 (2022): IJRTTE - 01 - 03
Section
Articles

References

  1. Y. Zhao, Z. Nie, K. Dong, Q. Huang, and X. Li, "Autonomous decision making for UAV cooperative pursuit-evasion game with reinforcement learning," arXiv preprint arXiv:2411.02983, 2024.R. Ferdous, F. Kifetew, D. Prandi, and A. Susi, "Curiosity Driven Multi-agent Reinforcement Learning for 3D Game Testing," arXiv preprint arXiv:2502.14606, 2025.arxiv.org
  2. F. Martinez-Lopez, J. Chen, and Y. Lu, "SPRIG: Stackelberg Perception-Reinforcement Learning with Internal Game Dynamics," arXiv preprint arXiv:2502.14264, 2025.arxiv.org
  3. Z. Jia, J. Li, X. Qu, and J. Wang, "Enhancing Multi-Agent Systems via Reinforcement Learning with LLM-based Planner and Graph-based Policy," arXiv preprint arXiv:2503.10049, 2025.arxiv.org
  4. J. Duan, W. Wang, and L. Xiao, "Distributional Soft Actor-Critic with Three Refinements," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 47, no. 1, pp. 1–14, 2025.
  5. S. Goodfriend, "A Competition Winning Deep Reinforcement Learning Agent in microRTS," arXiv preprint arXiv:2402.08112, 2024.
  6. Y. Yang and J. Wang, "An overview of multi-agent reinforcement learning from game theoretical perspective," arXiv preprint arXiv:2011.00583, 2020.arxiv.org
  7. K. Zhang, Z. Yang, and T. Başar, "Multi-agent reinforcement learning: A selective overview of theories and algorithms," in Handbook of Reinforcement Learning and Control, Springer, 2021, pp. 321–384.arxiv.org
  8. G. Papoudakis, F. Christianos, A. Rahman, and S. V. Albrecht, "Dealing with non-stationarity in multi-agent deep reinforcement learning," arXiv preprint arXiv:1906.04737, 2019.arxiv.org
  9. M. Gerstgrasser, T. Danino, and S. Keren, "Selectively sharing experiences improves multi-agent reinforcement learning," in Advances in Neural Information Processing Systems, vol. 36, 2024.arxiv.org
  10. L. Canese et al., "Multi-agent reinforcement learning: A review of challenges and applications," Applied Sciences, vol. 11, no. 11, 2021.arxiv.org
  11. D. Pathak, P. Agrawal, A. A. Efros, and T. Darrell, "Curiosity-driven exploration by self-supervised prediction," in Proceedings of the 34th International Conference on Machine Learning, 2017, pp. 2778–2787.arxiv.org
  12. W. J. Zhou et al., "Hierarchical control of multi-agent reinforcement learning team in real-time strategy (RTS) games," Expert Systems with Applications, vol. 186, 2021.arxiv.org
  13. Y. J. Park, Y. S. Cho, and S. B. Kim, "Multi-agent reinforcement learning with approximate model learning for competitive games," PLOS ONE, vol. 14, no. 9, p. e0222215, 2019.arxiv.org
  14. O. Vinyals et al., "Grandmaster level in StarCraft II using multi-agent reinforcement learning," Nature, vol. 575, no. 7782, pp. 350–354, 2019.arxiv.org
  15. D. Ye et al., "Towards Playing Full MOBA Games with Deep Reinforcement Learning," arXiv preprint arXiv:2011.12692, 2020.arxiv.org
  16. L. Greige and P. Chin, "Deep Reinforcement Learning for FlipIt Security Game," arXiv preprint arXiv:2002.12909, 2020.arxiv.org
  17. H. Liu and W. Wu, "Online Multi-agent Reinforcement Learning for Decentralized Inverter-based Volt-VAR Control," arXiv preprint arXiv:2006.12841, 2020.arxiv.org
  18. J. Schulman et al., "Proximal Policy Optimization Algorithms," arXiv preprint arXiv:1707.06347, 2017.
  19. T. Haarnoja et al., "Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor," in Proceedings of the 35th International Conference on Machine Learning, 2018, pp. 1861–1870.
  20. V. Mnih et al., "Asynchronous Methods for Deep Reinforcement Learning," in Proceedings of the 33rd International Conference on Machine Learning, 2016, pp. 1928–1937.
  21. H. van Hasselt, A. Guez, and D. Silver, "Deep Reinforcement Learning with Double Q-learning," in Proceedings of the 30th AAAI Conference on Artificial Intelligence, 2016, pp. 2094–2100.
  22. M. Hausknecht and P. Stone, "Deep Recurrent Q-Learning for Partially Observable MDPs," arXiv preprint arXiv:1507.06527, 2015.
  23. J. Schulman et al., "Trust Region Policy Optimization," in Proceedings of the 32nd International Conference on Machine Learning, 2015, pp. 1889–1897.
  24. T. P. Lillicrap et al., "Continuous control with deep reinforcement learning," arXiv preprint arXiv:1509.02971, 2015.
  25. D. Silver et al., "Deterministic Policy Gradient Algorithms," in Proceedings of the 31st International Conference on Machine Learning, 2014, pp. 387–395.
  26. M. Andrychowicz et al., "Hindsight Experience Replay," in Proceedings of the 31st International Conference on Neural Information Processing Systems, 2017, pp. 5048–5058.
  27. W. Dabney et al., "Distributional Reinforcement Learning with Quantile Regression," in Proceedings of the 32nd AAAI Conference on Artificial Intelligence, 2018, pp. 2892–2901.
  28. A. Tamar, Y. Glassner, and S. Mannor, "Optimizing the CVaR via Sampling," in Proceedings of the 29th AAAI Conference on Artificial Intelligence, 2015, pp. 2993–2999.
  29. A. Finn, P. Abbeel, and S. Levine, "Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks," in Proceedings of the 34th International Conference on Machine Learning, 2017, pp. 1126–1135.
  30. P. Henderson et al., "Deep Reinforcement Learning That Matters," in Proceedings of the 32nd AAAI Conference on Artificial Intelligence, 2018, pp. 3207–3214.
  31. A. Vaswani et al., "Attention Is All You Need," in Proceedings of the 31st International Conference on Neural Information Processing Systems, 2017, pp. 5998–6008.
  32. R. Lowe et al., "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments," in Proceedings of the 31st International Conference on Neural Information Processing Systems, 2017, pp. 6379–6390.
  33. J. Foerster et al., "Learning to communicate with deep multi-agent reinforcement learning," in Proceedings of the 30th International Conference on Neural Information Processing Systems, 2016, pp. 2137–2145.
  34. M. Jaderberg et al., "Human-level performance in 3D multiplayer games with population-based reinforcement learning," Science, vol. 364, no. 6443, pp. 859–865, 2019.
  35. Y. Duan et al., "Benchmarking Deep Reinforcement Learning for Continuous Control," in Proceedings of the 33rd International Conference on Machine Learning, 2016, pp. 1329–1338.
  36. R. S. Sutton and A. G. Barto, Reinforcement Learning: An Introduction, 2nd ed. MIT Press, 2018.