Abstract | ||
---|---|---|
We propose an efficient solution approach for high-dimensional nonlocal mean-field game (MFG) systems based on the Monte Carlo approximation of interaction kernels via random features. We avoid costly space-discretizations of interaction terms in the state-space by passing to the feature-space. This approach allows for a seamless mean-field extension of virtually any single-agent trajectory optimization algorithm. Here, we extend the direct transcription approach in optimal control to the mean-field setting. We demonstrate the efficiency of our method by solving MFG problems in high-dimensional spaces which were previously out of reach for conventional non-deep-learning techniques. |
Year | DOI | Venue |
---|---|---|
2022 | 10.1016/j.jcp.2022.111136 | Journal of Computational Physics |
Keywords | DocType | Volume |
Mean-field games,Nonlocal interactions,Random features,Optimal control,Hamilton-Jacobi-Bellman | Journal | 459 |
ISSN | Citations | PageRank |
0021-9991 | 0 | 0.34 |
References | Authors | |
0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Sudhanshu Agrawala | 1 | 0 | 0.34 |
Wonjun Lee | 2 | 0 | 0.68 |
Samy Wu Fung | 3 | 0 | 0.34 |
Levon Nurbekyan | 4 | 0 | 0.34 |