mirror of
https://github.com/Farama-Foundation/Gymnasium.git
synced 2025-08-20 05:52:03 +00:00
66 lines
2.1 KiB
Python
66 lines
2.1 KiB
Python
|
import logging
|
||
|
|
import os, sys
|
||
|
|
|
||
|
|
import gym
|
||
|
|
from gym.monitoring.live_plot import LivePlot
|
||
|
|
|
||
|
|
# The world's simplest agent!
|
||
|
|
class RandomAgent(object):
|
||
|
|
def __init__(self, action_space):
|
||
|
|
self.action_space = action_space
|
||
|
|
|
||
|
|
def act(self, observation, reward, done):
|
||
|
|
return self.action_space.sample()
|
||
|
|
|
||
|
|
if __name__ == '__main__':
|
||
|
|
# You can optionally set up the logger. Also fine to set the level
|
||
|
|
# to logging.DEBUG or logging.WARN if you want to change the
|
||
|
|
# amount of output.
|
||
|
|
logger = logging.getLogger()
|
||
|
|
logger.setLevel(logging.INFO)
|
||
|
|
|
||
|
|
env = gym.make('CartPole-v0' if len(sys.argv)<2 else sys.argv[1])
|
||
|
|
|
||
|
|
# 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.monitor.start(outdir, force=True, seed=0)
|
||
|
|
|
||
|
|
# You may optionally include a LivePlot so that you can see
|
||
|
|
# how your agent is performing. Use plotter.plot() to update
|
||
|
|
# the graph.
|
||
|
|
plotter = LivePlot(outdir)
|
||
|
|
|
||
|
|
# This declaration must go *after* the monitor call, since the
|
||
|
|
# monitor's seeding creates a new action_space instance with the
|
||
|
|
# appropriate pseudorandom number generator.
|
||
|
|
agent = RandomAgent(env.action_space)
|
||
|
|
|
||
|
|
episode_count = 100
|
||
|
|
max_steps = 200
|
||
|
|
reward = 0
|
||
|
|
done = False
|
||
|
|
|
||
|
|
for i in range(episode_count):
|
||
|
|
ob = env.reset()
|
||
|
|
|
||
|
|
for j in range(max_steps):
|
||
|
|
action = agent.act(ob, reward, done)
|
||
|
|
ob, reward, done, _ = env.step(action)
|
||
|
|
if done:
|
||
|
|
break
|
||
|
|
|
||
|
|
plotter.plot()
|
||
|
|
env.render()
|
||
|
|
|
||
|
|
|
||
|
|
# Dump result info to disk
|
||
|
|
env.monitor.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, algorithm_id='random')
|