From the 1 of 3 linked papers with an AI index.
3 papers
Augmentations for Robust and Efficient Imitation Learning in Streamed Video Games
Somjit Nath, Abdelhak Lemkhenter, Pallavi Choudhury +4
The paper introduces spatiotemporal data augmentations that mimic streaming artifacts (pixelation, blur, ghosting, etc.) to improve the robustness and efficiency of imitation‑learn…
When Does Predictive Inverse Dynamics Outperform Behavior Cloning?
Lukas Schäfer, Pallavi Choudhury, Abdelhak Lemkhenter +10
Behavior cloning (BC) is a practical offline imitation learning method, but it often fails when expert demonstrations are limited. Recent works have introduced a class of architect…
Adapting a World Model for Trajectory Following in a 3D Game
Marko Tot, Shu Ishida, Abdelhak Lemkhenter +10
Imitation learning is a powerful tool for training agents by leveraging expert knowledge, and being able to replicate a given trajectory is an integral part of it. In complex envir…