Table 1: Whether it is able to tolerate according to the different momentum for [1] and our policy network. The ‘T’ means that the character tolerates such momentum, and the ‘F’ means that the character fall down at such momentum.

Time(s) Other [1] Our policy network
0.01 T T
0.1 T T
0.2 T T
0.3 T T
0.4 F T
1.0 F T