Adaptive Incentive Design with Learning Agents
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917941411315712 |
|---|---|
| author | Maheshwari, Chinmay Kulkarni, Kshitij Wu, Manxi Sastry, Shankar |
| author_facet | Maheshwari, Chinmay Kulkarni, Kshitij Wu, Manxi Sastry, Shankar |
| contents | 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. Additionally, we provide sufficient conditions under which the adaptive mechanism converges to a fixed point. Our results apply to both atomic and non-atomic games. To demonstrate the effectiveness of our proposed mechanism, we verify the convergence conditions in two practically relevant classes of games: atomic aggregative games and non-atomic routing games. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_16716 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Adaptive Incentive Design with Learning Agents Maheshwari, Chinmay Kulkarni, Kshitij Wu, Manxi Sastry, Shankar Computer Science and Game Theory Multiagent Systems Systems and Control Dynamical Systems 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. Additionally, we provide sufficient conditions under which the adaptive mechanism converges to a fixed point. Our results apply to both atomic and non-atomic games. To demonstrate the effectiveness of our proposed mechanism, we verify the convergence conditions in two practically relevant classes of games: atomic aggregative games and non-atomic routing games. |
| title | Adaptive Incentive Design with Learning Agents |
| topic | Computer Science and Game Theory Multiagent Systems Systems and Control Dynamical Systems |
| url | https://arxiv.org/abs/2405.16716 |