はてなブックマーク

DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skills Transactions on Graphics (Proc. ACM SIGGRAPH 2018) Xue Bin Peng (1)    Pieter Abbeel (1)    Sergey Levine (1)    Michiel van de Panne (2) (1) University of California, Berkeley    (2) University of British Columbia Abstract A longstanding goal in character animation is to combine data-driven specification of be