**ALLSTEPS: Curriculum-driven Learning of Stepping Stone Skills**
**Zhaoming Xie, Hung Yu Ling, Nam Hee Kim, Michiel van de Panne
University of British Columbia**
![](allsteps2.png height="150px" border="1") ![](allsteps3.png height="150px" border="1") ![](allsteps1.png height="150px" border="1") __Abstract__ Humans are highly adept at walking in environments with foot placement constraints, including stepping-stone scenarios where the footstep locations are fully constrained. Finding good solutions to stepping-stone locomotion is a longstanding and fundamental challenge for animation and robotics. We present fully learned solutions to this difficult problem using reinforcement learning. We demonstrate the importance of a curriculum for efficient learning and evaluate four possible curriculum choices compared to a non-curriculum baseline. Results are presented for a simulated human character, a realistic bipedal robot simulation and a monster character,in each case producing robust, plausible motions for challenging stepping stone sequences and terrains. __Paper__ [PDF](allsteps-arxiv-small.pdf) preprint
[ArXiV page](https://arxiv.org/abs/2005.04323) __Video__ __bibtex__ ````````````````````````` @inproceedings{2020-ALLSTEPS, title={ALLSTEPS: Curriculum-driven Learning of Stepping Stone Skills}, author={Zhaoming Xie and Hung Yu Ling and Nam Hee Kim and Michiel van de Panne}, eprint={2005.04323}, archivePrefix={arXiv}, primaryClass={cs.GR} year={2020} } `````````````````````````