mirror of
https://github.com/Farama-Foundation/Gymnasium.git
synced 2025-08-26 16:27:11 +00:00
4c460ba6c8
* add dtype to Box
* remove board_game, debugging, safety, parameter_tuning environments
* massive set of breaking changes
- remove python logging module
- _step, _reset, _seed, _close => non underscored method
- remove benchmark and scoring folder
* Improve render("human"), now resizable, closable window.
* get rid of default step and reset in wrappers, so it doesn’t silently fail for people with underscore methods
* CubeCrash unit test environment
* followup fixes
* MemorizeDigits unit test envrionment
* refactored spaces a bit
fixed indentation
disabled test_env_semantics
* fix unit tests
* fixes
* CubeCrash, MemorizeDigits tested
* gym backwards compatibility patch
* gym backwards compatibility, followup fixes
* changelist, add spaces to main namespaces
* undo_logger_setup for backwards compat
* remove configuration.py
52 lines
1.7 KiB
Python
52 lines
1.7 KiB
Python
import argparse
|
|
import sys
|
|
|
|
import gym
|
|
from gym import wrappers, logger
|
|
|
|
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()
|
|
|
|
# You can set the level to logger.DEBUG or logger.WARN if you
|
|
# want to change the amount of output.
|
|
logger.set_level(logger.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(env, directory=outdir, force=True)
|
|
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()
|