mirror of
https://github.com/Farama-Foundation/Gymnasium.git
synced 2025-08-18 04:49:12 +00:00
2d44ed4968
* Add WIP Monitored wrapper * Remove irrelevant render after close monitor test * py27 compatibility * Fix test_benchmark * Move Monitored out of wrappers __init__ * Turn Monitored into a function that returns a Monitor class * Fix monitor tests * Remove deprecated test * Remove deprecated utility * Prevent duplicate wrapping, add test * Fix test * close env in tests to prevent writing to nonexistent file * Disable semisuper tests * typo * Fix failing spec * Fix monitoring on semisuper tasks * Allow disabling of duplicate check * Rename MonitorManager * Monitored -> Monitor * Clean up comments * Remove cruft
69 lines
2.4 KiB
Python
69 lines
2.4 KiB
Python
import argparse
|
|
import logging
|
|
import sys
|
|
|
|
import gym
|
|
from gym import wrappers
|
|
|
|
|
|
class RandomAgent(object):
|
|
"""The world's simplest agent!"""
|
|
def __init__(self, action_space):
|
|
self.action_space = action_space
|
|
|
|
def act(self, observation, reward, done):
|
|
return self.action_space.sample()
|
|
|
|
if __name__ == '__main__':
|
|
parser = argparse.ArgumentParser(description=None)
|
|
parser.add_argument('env_id', nargs='?', default='CartPole-v0', help='Select the environment to run')
|
|
args = parser.parse_args()
|
|
|
|
# Call `undo_logger_setup` if you want to undo Gym's logger setup
|
|
# and configure things manually. (The default should be fine most
|
|
# of the time.)
|
|
gym.undo_logger_setup()
|
|
logger = logging.getLogger()
|
|
formatter = logging.Formatter('[%(asctime)s] %(message)s')
|
|
handler = logging.StreamHandler(sys.stderr)
|
|
handler.setFormatter(formatter)
|
|
logger.addHandler(handler)
|
|
|
|
# You can set the level to logging.DEBUG or logging.WARN if you
|
|
# want to change the amount of output.
|
|
logger.setLevel(logging.INFO)
|
|
|
|
env = gym.make(args.env_id)
|
|
|
|
# You provide the directory to write to (can be an existing
|
|
# directory, including one with existing data -- all monitor files
|
|
# will be namespaced). You can also dump to a tempdir if you'd
|
|
# like: tempfile.mkdtemp().
|
|
outdir = '/tmp/random-agent-results'
|
|
env = wrappers.Monitor(directory=outdir, force=True)(env)
|
|
env.seed(0)
|
|
agent = RandomAgent(env.action_space)
|
|
|
|
episode_count = 100
|
|
reward = 0
|
|
done = False
|
|
|
|
for i in range(episode_count):
|
|
ob = env.reset()
|
|
while True:
|
|
action = agent.act(ob, reward, done)
|
|
ob, reward, done, _ = env.step(action)
|
|
if done:
|
|
break
|
|
# Note there's no env.render() here. But the environment still can open window and
|
|
# render if asked by env.monitor: it calls env.render('rgb_array') to record video.
|
|
# Video is not recorded every episode, see capped_cubic_video_schedule for details.
|
|
|
|
# Close the env and write monitor result info to disk
|
|
env.close()
|
|
|
|
# Upload to the scoreboard. We could also do this from another
|
|
# process if we wanted.
|
|
logger.info("Successfully ran RandomAgent. Now trying to upload results to the scoreboard. If it breaks, you can always just try re-uploading the same results.")
|
|
gym.upload(outdir)
|