INTELLIGENT BARGAINING AGENTS IN DIGITAL MARKETPLACES: A FUSION OF REINFORCEMENT LEARNING AND GAME-THEORETIC PRINCIPLES
DOI:
https://doi.org/10.55640/ijaair-v02i03-02Keywords:
Autonomous negotiation, e-commerce, reinforcement learning, game theoryAbstract
The burgeoning landscape of e-commerce has transformed traditional marketplaces, giving rise to complex, dynamic environments where automated negotiation agents can play a pivotal role. Effective autonomous negotiation requires agents to not only understand their own objectives but also to strategically interact with and adapt to the behaviors of other participants. This article provides a comprehensive review of the synergistic integration of reinforcement learning (RL) and game theory (GT) to develop intelligent bargaining agents for digital marketplaces. We delve into how RL enables agents to learn optimal negotiation strategies through experience, even in environments with imperfect information and unknown opponents, while GT provides the theoretical foundation for rational decision-making, equilibrium analysis, and strategic interactions. By synthesizing empirical findings from various applications, including multi-issue bargaining and team formation, we illustrate the distinct advantages of combining these paradigms over purely isolated approaches. Furthermore, we address the current limitations of such hybrid frameworks and outline critical future research directions towards building more robust, adaptive, and human-like negotiation agents in e-commerce.
References
Chang, H.-C. H. (2020). Multi-issue bargaining with deep reinforcement learning. arXiv:2002.07788.
Bagga, P., Paoletti, N., Alrayes, B., & Stathis, K. (2020). A deep reinforcement learning approach to concurrent bilateral negotiation. arXiv:2001.11785.
Sengupta, A., Mohammad, Y., & Nakadai, S. (2021). An autonomous negotiating agent framework with reinforcement learning based strategies and adaptive strategy switching mechanism. arXiv:2102.03588.
Chang, H.-C. H. (2021). Negotiating team formation using deep reinforcement learning. arXiv:2010.10380.
Li, Z., Lanctot, M., McKee, K. R., Marris, L., Gemp, I., Hennes, D., Larson, K., Bachrach, Y., Wellman, M. P., & Muller, P. (2023). Search improved game theoretic multiagent reinforcement learning in general and negotiation games. AAMAS 2023 (extended abstract).
Bagga, P., Paoletti, N., Alrayes, B., & Stathis, K. (2021). ANEGMA: An automated negotiation model for e-markets. Autonomous Agents and Multi-Agent Systems, 35, Article 27.
Binmore, K., & Vulkan, N. (1999). Applying game theory to automated negotiation. Netnomics, 1, 1–9.
Schmid, K., Belzner, L., Phan, T., Gabor, T., & Linnhoff-Popien, C. (2020). Multi-agent reinforcement learning for bargaining under risk and asymmetric information. Proceedings of SCITEPRESS, 89139.
Rams, R. P., & Zeng, D. (1997). Benefits of learning in negotiation. In Proceedings of the AAAI National Conference on Artificial Intelligence (pp. 36–41).
Sim, K. M., Guo, Y., & Shi, B. (2007). Adaptive bargaining agents that negotiate optimally and rapidly. In IEEE Congress on Evolutionary Computation (pp. 1007–1014).
Tesauro, G., & Kephart, J. O. (2000). Pricing in agent economies using multi-agent Q-learning. Autonomous Agents and Multi-Agent Systems, 3(1), 1–24.
Cai, T., Wang, Y., Weinberger, K. Q., & Chen, Z. (2019). Neural logic machines. NeurIPS.
Rocktäschel, T., & Riedel, S. (2017). End-to-end differentiable proving. NeurIPS.
Greenwald, A. R., & Wellman, M. P. (2007). Autonomous bidding agents: Strategies and lessons from the Trading Agent Competition. MIT Press.
Kraus, S. (2001). Strategic negotiation and the integration of game theory and AI: The Diplomat agent. In Principles of Negotiating Agents (pp. 1–15).
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Dr. Arvind Patel, Anamika Mishra (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors retain the copyright of their manuscripts, and all Open Access articles are disseminated under the terms of the Creative Commons Attribution License 4.0 (CC-BY), which licenses unrestricted use, distribution, and reproduction in any medium, provided that the original work is appropriately cited. The use of general descriptive names, trade names, trademarks, and so forth in this publication, even if not specifically identified, does not imply that these names are not protected by the relevant laws and regulations.