fancy_gym/dmp_pd_control_example.py

32 lines
962 B
Python
Raw Normal View History

2021-04-10 19:11:32 +02:00
from alr_envs.mujoco.ball_in_a_cup.utils import make_env, make_simple_env, make_simple_dmp_env
2021-02-15 09:03:19 +01:00
from alr_envs.utils.dmp_async_vec_env import DmpAsyncVectorEnv
2021-02-05 17:10:03 +01:00
import numpy as np
2021-04-13 09:51:34 +02:00
from gym import wrappers
2021-02-05 17:10:03 +01:00
if __name__ == "__main__":
2021-04-08 11:05:47 +02:00
dim = 15
2021-02-15 09:03:19 +01:00
n_cpus = 4
2021-03-26 14:30:58 +01:00
# n_samples = 10
2021-02-15 09:03:19 +01:00
#
2021-03-26 14:30:58 +01:00
# vec_env = DmpAsyncVectorEnv([make_simple_env(i) for i in range(n_cpus)],
# n_samples=n_samples)
2021-02-15 09:03:19 +01:00
#
2021-03-26 14:30:58 +01:00
# params = np.tile(1 * np.random.randn(n_samples, dim), (10, 1))
#
# rewards, infos = vec_env(params)
# print(rewards)
#
2021-04-10 19:11:32 +02:00
non_vec_env = make_simple_dmp_env(0, 0)()
2021-03-26 14:30:58 +01:00
2021-04-08 11:05:47 +02:00
# params = 0.5 * np.random.randn(dim)
2021-04-13 09:51:34 +02:00
params = np.array([-2.63357598, -1.04950296, -0.44330737, 0.52950017, 4.29247739,
4.52473661, -0.05685977, -0.76796851, 3.71540499, 1.22631059,
2.20412438, 3.91588129, -0.12652723, -3.0788211 , 0.56204464])
2021-02-05 17:10:03 +01:00
2021-04-13 09:51:34 +02:00
out2 = non_vec_env.rollout(params, render=True )
2021-02-05 17:10:03 +01:00
2021-03-26 14:30:58 +01:00
print(out2)