mirror of
https://github.com/vale981/ray
synced 2025-03-10 05:16:49 -04:00
026bf01071
* Fix QMix, SAC, and MADDPA too. * Unpin gym and deprecate pendulum v0 Many tests in rllib depended on pendulum v0, however in gym 0.21, pendulum v0 was deprecated in favor of pendulum v1. This may change reward thresholds, so will have to potentially rerun all of the pendulum v1 benchmarks, or use another environment in favor. The same applies to frozen lake v0 and frozen lake v1 Lastly, all of the RLlib tests and have been moved to python 3.7 * Add gym installation based on python version. Pin python<= 3.6 to gym 0.19 due to install issues with atari roms in gym 0.20 * Reformatting * Fixing tests * Move atari-py install conditional to req.txt * migrate to new ale install method * Fix QMix, SAC, and MADDPA too. * Unpin gym and deprecate pendulum v0 Many tests in rllib depended on pendulum v0, however in gym 0.21, pendulum v0 was deprecated in favor of pendulum v1. This may change reward thresholds, so will have to potentially rerun all of the pendulum v1 benchmarks, or use another environment in favor. The same applies to frozen lake v0 and frozen lake v1 Lastly, all of the RLlib tests and have been moved to python 3.7 * Add gym installation based on python version. Pin python<= 3.6 to gym 0.19 due to install issues with atari roms in gym 0.20 Move atari-py install conditional to req.txt migrate to new ale install method Make parametric_actions_cartpole return float32 actions/obs Adding type conversions if obs/actions don't match space Add utils to make elements match gym space dtypes Co-authored-by: Jun Gong <jungong@anyscale.com> Co-authored-by: sven1977 <svenmika1977@gmail.com>
43 lines
1.4 KiB
Python
43 lines
1.4 KiB
Python
import unittest
|
|
|
|
import ray
|
|
import ray.rllib.agents.es as es
|
|
from ray.rllib.utils.test_utils import check_compute_single_action, \
|
|
framework_iterator
|
|
|
|
|
|
class TestES(unittest.TestCase):
|
|
def test_es_compilation(self):
|
|
"""Test whether an ESTrainer can be built on all frameworks."""
|
|
ray.init(num_cpus=4)
|
|
config = es.DEFAULT_CONFIG.copy()
|
|
# Keep it simple.
|
|
config["model"]["fcnet_hiddens"] = [10]
|
|
config["model"]["fcnet_activation"] = None
|
|
config["noise_size"] = 2500000
|
|
config["num_workers"] = 1
|
|
config["episodes_per_batch"] = 10
|
|
config["train_batch_size"] = 100
|
|
# Test eval workers ("normal" Trainer eval WorkerSet).
|
|
config["evaluation_interval"] = 1
|
|
config["evaluation_num_workers"] = 2
|
|
|
|
num_iterations = 1
|
|
|
|
for _ in framework_iterator(config):
|
|
for env in ["CartPole-v0", "Pendulum-v1"]:
|
|
plain_config = config.copy()
|
|
trainer = es.ESTrainer(config=plain_config, env=env)
|
|
for i in range(num_iterations):
|
|
results = trainer.train()
|
|
print(results)
|
|
|
|
check_compute_single_action(trainer)
|
|
trainer.stop()
|
|
ray.shutdown()
|
|
|
|
|
|
if __name__ == "__main__":
|
|
import pytest
|
|
import sys
|
|
sys.exit(pytest.main(["-v", __file__]))
|