Skip to main content
GameDev.net gamedev.net
2 sources covering this story

HIL: Hybrid Imitation Learning of Diverse Parkour Skills from Videos

This paper shows a way to train one controller that can both mimic reference parkour motion and still adapt when the environment changes. For teams working on character movement, the interesting bit is the hybrid setup: motion tracking for fidelity, adversarial imitation for robustness. The result is more diverse athletic behaviors without giving up much naturalness.

First reported 3 months ago ai animation locomotion parkour
Want to discuss what this means for developers?
Open discussion
PRIMARY SOURCE
arXiv cs.GR arXiv cs.GR

HIL: Hybrid Imitation Learning of Diverse Parkour Skills from Videos

3 months ago Read source
arXiv cs.GR arXiv cs.GR 1% match

High-Fidelity 3D Geometric Reconstruction of Pelvic Organs from MRI: A Hybrid Deep Learning and Iterative Optimization Approach

3 months ago Read source