mirror of
https://github.com/Farama-Foundation/Gymnasium.git
synced 2025-08-18 21:06:59 +00:00
58e6aa95e5
* Make environments seedable * Fix monitor bugs - Set monitor_id before setting the infix. This was a bug that would yield incorrect results with multiple monitors. - Remove extra pid from stats recorder filename. This should be purely cosmetic. * Start uploading seeds in episode_batch * Fix _bigint_from_bytes for python3 * Set seed explicitly in random_agent * Pass through seed argument * Also pass through random state to spaces * Pass random state into the observation/action spaces * Make all _seed methods return the list of used seeds * Switch over to np.random where possible * Start hashing seeds, and also seed doom engine * Fixup seeding determinism in many cases * Seed before loading the ROM * Make seeding more Python3 friendly * Make the MuJoCo skipping a bit more forgiving * Remove debugging PDB calls * Make setInt argument into raw bytes * Validate and upload seeds * Skip box2d * Make seeds smaller, and change representation of seeds in upload * Handle long seeds * Fix RandomAgent example to be deterministic * Handle integer types correctly in Python2 and Python3 * Try caching pip * Try adding swap * Add df and free calls * Bump swap * Bump swap size * Try setting overcommit * Try other sysctls * Try fixing overcommit * Try just setting overcommit_memory=1 * Add explanatory comment * Add what's new section to readme * BUG: Mark ElevatorAction-ram-v0 as non-deterministic for now * Document seed * Move nondetermistic check into spec
59 lines
2.1 KiB
Python
59 lines
2.1 KiB
Python
import logging
|
|
import os, sys
|
|
|
|
import gym
|
|
|
|
# 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)
|
|
|
|
# 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
|
|
# 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.
|
|
|
|
# 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')
|