Why is state value not same as env.sim.get_state().qpos and env.sim.get_state().qvel ?

[rebecajohn]

Why is state value not same as env.sim.get_state().qpos and env.sim.get_state().qvel ?

CODE:

import gym
import d4rl

env = gym.make('hopper-expert-v2')

state = env.reset()
print(state)
print("***********************")

Get qpos and qvel

Qpos = [env.sim.get_state().qpos]
Qvel = [env.sim.get_state().qvel]
print(Qpos)
print("")
print(Qvel)
print("")

Output:

[ 1.24992675e+00 6.55631079e-04 1.55495303e-03 -4.53425491e-03
4.51943952e-03 -1.02679957e-03 -8.93176844e-04 3.55990965e-03
-3.02509415e-03 -4.76351951e-03 6.71493509e-04]

---

[array([ 2.55533055e-03, 1.24992675e+00, 6.55631079e-04, 1.55495303e-03,
-4.53425491e-03, 4.51943952e-03])]

---

[array([-0.0010268 , -0.00089318, 0.00355991, -0.00302509, -0.00476352,
0.00067149])]

---