Conference
Open access
Oct 2026
A Mixture of Domain Experts Framework for Autonomous Navigation via Deep Reinforcement Learning
Long-horizon evaluations across in-distribution and held-out CARLA towns show that the proposed architecture outperforms monolithic and end-to-end MoE baselines, especially under multi-scenario and out-of-distribution conditions.
V. Neves, Ana Huamán Reyna, I. P. Gomes et al.
· International Conference on... · 0 citations