ALLSTEPS: Curriculum-driven Learning of Stepping Stone Skills
| dc.contributor.author | Xie, Zhaoming | en_US |
| dc.contributor.author | Ling, Hung Yu | en_US |
| dc.contributor.author | Kim, Nam Hee | en_US |
| dc.contributor.author | Panne, Michiel van de | en_US |
| dc.contributor.editor | Bender, Jan and Popa, Tiberiu | en_US |
| dc.date.accessioned | 2020-10-16T06:25:57Z | |
| dc.date.available | 2020-10-16T06:25:57Z | |
| dc.date.issued | 2020 | |
| dc.description.abstract | Humans are highly adept at walking in environments with foot placement constraints, including stepping-stone scenarios where 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 humanoid, a realistic bipedal robot simulation and a monster character, in each case producing robust, plausible motions for challenging stepping stone sequences and terrains. | en_US |
| dc.description.number | 8 | |
| dc.description.sectionheaders | Character Animation 1 | |
| dc.description.seriesinformation | Computer Graphics Forum | |
| dc.description.volume | 39 | |
| dc.identifier.doi | 10.1111/cgf.14115 | |
| dc.identifier.issn | 1467-8659 | |
| dc.identifier.pages | 213-224 | |
| dc.identifier.uri | https://doi.org/10.1111/cgf.14115 | |
| dc.identifier.uri | https://diglib.eg.org:443/handle/10.1111/cgf14115 | |
| dc.publisher | The Eurographics Association and John Wiley & Sons Ltd. | en_US |
| dc.subject | Computing methodologies | |
| dc.subject | Reinforcement learning | |
| dc.subject | Physical simulation | |
| dc.title | ALLSTEPS: Curriculum-driven Learning of Stepping Stone Skills | en_US |