Yuntian Zhang

A latent world model slashes navigation planning costs by 128x while boosting real-robot success rates from 43% to 83% in unseen environments.

Adversarial training with deep reinforcement learning cracks the computationally intractable Maximal Covering Location-Interdiction Problem, outperforming traditional methods in speed and solution quality.

DRL agents can now solve vehicle routing problems across diverse real-world distributions thanks to a new architecture that adaptively recombines specialized policy modules.