Adaptive Incentive Design With Learning Agents

• 成果类型: Article
• 署名作者: Maheshwari, Chinmay; Kulkarni, Kshitij; Wu, Manxi; Sastry, Shankar
• 署名单位: Johns Hopkins University; University of California System; University of California Berkeley; University of California System; University of California Berkeley
• 刊物名称: IEEE TRANSACTIONS ON AUTOMATIC CONTROL
• ISSN/ISSBN: 0018-9286
• DOI: 10.1109/TAC.2025.3643351
• 发表日期: 2026
• 关键词: stochastic-approximation; RESPONSE DYNAMICS; systems

摘要

In this artice, we propose an adaptive incentive mechanism that learns the optimal incentives in environments where players continuously update their strategies. Our mechanism updates incentives based on each player's externality, defined as the difference between the player's marginal cost and the operator's marginal cost at each time step. The proposed mechanism updates the incentives on a slower timescale compared to the players' learning dynamics, resulting in a two-timescale coupled dynamical system. Notably, this mechanism is agnostic to the specific learning dynamics used by players to update their strategies. We show that any fixed point of this adaptive incentive mechanism corresponds to the optimal incentive mechanism, ensuring that the Nash equilibrium coincides with the socially optimal strategy. In addition, we provide sufficient conditions under which the adaptive mechanism converges to a fixed point. Our results apply to both atomic and nonatomic games. To demonstrate the effectiveness of our proposed mechanism, we verify the convergence conditions in two practically relevant classes of games: 1) atomic aggregative games; and 2) nonatomic routing games.