blob: b52b945ad04606d7c7a83974e15dafb9af45100e (
plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
|
"""An example to run the gym environment that a minitaur follows a ball.
"""
import math
import tensorflow as tf
import minitaur_ball_gym_env
def FollowBallManualPolicy():
"""An example of a minitaur following a ball."""
env = minitaur_ball_gym_env.MinitaurBallGymEnv(render=True,
pd_control_enabled=True,
on_rack=False)
observation = env.reset()
sum_reward = 0
steps = 100000
for _ in range(steps):
action = [math.tanh(observation[0] * 4)]
observation, reward, done, _ = env.step(action)
sum_reward += reward
if done:
tf.logging.info("Return is {}".format(sum_reward))
observation = env.reset()
sum_reward = 0
def main():
FollowBallManualPolicy()
if __name__ == '__main__':
main()
|
