blob: 9b06bcfb2f9247667c80a6399aa8a1924e368c15 (
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
35
36
37
38
39
40
41
|
#add parent dir to find package. Only needed for source code build, pip install doesn't need it.
import os, inspect
currentdir = os.path.dirname(os.path.abspath(inspect.getfile(inspect.currentframe())))
parentdir = os.path.dirname(os.path.dirname(currentdir))
os.sys.path.insert(0, parentdir)
import gym
from pybullet_envs.bullet.racecarGymEnv import RacecarGymEnv
from baselines import deepq
import datetime
def callback(lcl, glb):
# stop training if reward exceeds 199
total = sum(lcl['episode_rewards'][-101:-1]) / 100
totalt = lcl['t']
is_solved = totalt > 2000 and total >= -50
return is_solved
def main():
env = RacecarGymEnv(renders=False, isDiscrete=True)
model = deepq.models.mlp([64])
act = deepq.learn(env,
q_func=model,
lr=1e-3,
max_timesteps=10000,
buffer_size=50000,
exploration_fraction=0.1,
exploration_final_eps=0.02,
print_freq=10,
callback=callback)
print("Saving model to racecar_model.pkl")
act.save("racecar_model.pkl")
if __name__ == '__main__':
main()
|