A bilevel optimization framework with normalizing flows recovers the latent obstacle and optimal trajectories in mean-field games from partial trajectory data, achieving about 0.1 relative L2 error even with fewer than 100 trajectories.
Inverse reinforcement learning., 2010
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Joint Inference of Trajectory and Obstacle in Mean-Field Games via Bilevel Optimization
A bilevel optimization framework with normalizing flows recovers the latent obstacle and optimal trajectories in mean-field games from partial trajectory data, achieving about 0.1 relative L2 error even with fewer than 100 trajectories.