Skip to content

Instantly share code, notes, and snippets.

@taotao54321
Created November 8, 2016 07:28
Show Gist options
  • Save taotao54321/18a9e20561c489dd4b80ef2b71c5a603 to your computer and use it in GitHub Desktop.
Save taotao54321/18a9e20561c489dd4b80ef2b71c5a603 to your computer and use it in GitHub Desktop.
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
import sys
import gym
DEBUG = False
#DEBUG = True
ENVS = {
"4x4" : "FrozenLake-v0",
"8x8" : "FrozenLake8x8-v0",
}
def error(msg):
sys.exit(msg)
def usage():
error("Usage: FrozenLake-random <4x4|8x8> <test_count>")
def main():
if len(sys.argv) != 3: usage()
env_name = ENVS[sys.argv[1]]
test_count = int(sys.argv[2])
print("# <{}>".format(env_name))
env = gym.make(env_name)
reward_total = 0.0
for episode in range(test_count):
ob = env.reset()
if DEBUG: env.render()
while True:
ob, reward, done, info = env.step(env.action_space.sample())
if DEBUG:
env.render()
print(ob, reward, done, info)
if done:
reward_total += reward
break
print("episodes: {}".format(test_count))
print("total reward: {}".format(reward_total))
print("average reward: {:.3f}".format(reward_total / test_count))
if __name__ == "__main__": main()
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment