how many kinds of actions does the MACE output

xbpeng / DeepTerrainRL

terrain-adaptive locomotion skills using deep reinforcement learning

GNU Lesser General Public License v3.0

432 stars 129 forks source link

how many kinds of actions does the MACE output #26

Open wenyijiang opened 7 years ago

wenyijiang commented 7 years ago

hi ! I want to know how many kinds of actions does the MACE output? and what is the difference between run and leap in your paper. thanks a lot ! best wishes!

xbpeng commented 7 years ago

our policies are a fixture of 3 actors. The difference between and run and a leap is mainly that the leap travels farther than the run. But they all use the same action parameterization of the finite state machine.