Article

FOCUS: A First-Order Control Method for Observation-Only Imitation Learning Supervised by Optimal Transport

FOCUS combines local optimal transport alignment with short-horizon differentiable actor-critic learning for observation-only imitation learning, requiring neither temporally aligned expert trajectories nor expert-aligned initialization. The method matches agent rollout windows to multiple sampled expert segments using a soft best-of-K objective, with the transport cost providing a differentiable imitation reward and a learned critic bootstrapping value beyond the rollout horizon.

Part of the event: FOCUS: Optimal Transport-Supervised Observation-Only Imitation Learning

This page provides a summary and source link only.