the duck learnt to sit and stand on command.
15,000 iterations of PPO in 4h32min on my RTX 5090, 4096 MuJoCo environments in parallel. mean reward 1.7 at iteration 0, 133 at the end.
in the clip: stand at 116 mm, sit at 59 mm, each switch under a second, and it holds the pose until the next command.
third skill in the tree after walking and getting up!
더 보기
