Autor: |
Somdeb Majumdar, Zhengfei Wang, Lance Rane, Zeyang Yu, Marcel Salathé, Aditya Bhatt, Ruihan Yang, Aleksandra Malysheva, Fan Wang, Łukasz Kidziński, Jeremy D. Watson, Bo Zhou, Rongzhong Lian, Aleksei Shpilman, Zhen Wang, Sharada P. Mohanty, Sergey Kolesnikov, Jennifer L. Hicks, Quan Yuan, Hao Tian, Carmichael F. Ong, Wojciech Jaśkowski, Yunsheng Tian, Nihat Engin Toklu, Shauharda Khadka, Minghui Qiu, Yinyin Liu, Sean F. Carroll, Ivan Sosin, Rupesh Kumar Srivastava, Xu Hu, Evren Tumer, Pranav Shyam, Scott L. Delp, Oleg Svidchenko, Daniel Kudenko, Oleksii Hrinchuk, Odd Rune Lykkebø, Wenxin Li, Sergey Levine, Mattias Ljungström, Pingchuan Ma, Zehong Hu, Hongsheng Zeng, Anton Pechenko, Zach Dwiel, Jun Huang, Peng Peng, Penghui Qi, Garrett Andersen |
Rok vydání: |
2019 |
Předmět: |
|
Zdroj: |
The NeurIPS '18 Competition ISBN: 9783030291341 |
Popis: |
In the NeurIPS 2018 Artificial Intelligence for Prosthetics challenge, participants were tasked with building a controller for a musculoskeletal model with a goal of matching a given time-varying velocity vector. Top participants described their algorithms in this paper. Many solutions use similar relaxations and heuristics, such as reward shaping, frame skipping, discretization of the action space, symmetry, and policy blending. However, each team implemented different modifications of the known algorithms by, for example, dividing the task into subtasks, learning low-level control, or by incorporating expert knowledge and using imitation learning. |
Databáze: |
OpenAIRE |
Externí odkaz: |
|