mirror of
https://github.com/vale981/ray
synced 2025-03-09 12:56:46 -04:00
5ac5ac9560
* WIP. * Fix float32 conversion in OneHot preprocessor (would cause float64 in eager, then NN-matmul-failure). Add proper seq-len + state-in construction in eager_tf_policy.py::_compute_gradients(). * LINT. * eager_tf_policy.py: Only set samples["seq_lens"] if RNN. Otherwise, eager-tracing will throw flattened-dict key-mismatch error. * Move issue code to examples folder. Co-authored-by: Eric Liang <ekhliang@gmail.com>
70 lines
1.8 KiB
Python
70 lines
1.8 KiB
Python
import unittest
|
|
|
|
import ray
|
|
from ray import tune
|
|
from ray.rllib.agents.registry import get_agent_class
|
|
|
|
|
|
def check_support(alg, config, test_trace=True):
|
|
config["eager"] = True
|
|
if alg in ["APEX_DDPG", "TD3", "DDPG", "SAC"]:
|
|
config["env"] = "Pendulum-v0"
|
|
else:
|
|
config["env"] = "CartPole-v0"
|
|
a = get_agent_class(alg)
|
|
config["log_level"] = "ERROR"
|
|
|
|
config["eager_tracing"] = False
|
|
tune.run(a, config=config, stop={"training_iteration": 0})
|
|
|
|
if test_trace:
|
|
config["eager_tracing"] = True
|
|
tune.run(a, config=config, stop={"training_iteration": 0})
|
|
|
|
|
|
class TestEagerSupport(unittest.TestCase):
|
|
def setUp(self):
|
|
ray.init(num_cpus=4)
|
|
|
|
def tearDown(self):
|
|
ray.shutdown()
|
|
|
|
def testSimpleQ(self):
|
|
check_support("SimpleQ", {"num_workers": 0, "learning_starts": 0})
|
|
|
|
def testDQN(self):
|
|
check_support("DQN", {"num_workers": 0, "learning_starts": 0})
|
|
|
|
def testA2C(self):
|
|
check_support("A2C", {"num_workers": 0})
|
|
|
|
def testA3C(self):
|
|
check_support("A3C", {"num_workers": 1})
|
|
|
|
def testPG(self):
|
|
check_support("PG", {"num_workers": 0})
|
|
|
|
def testPPO(self):
|
|
check_support("PPO", {"num_workers": 0})
|
|
|
|
def testAPPO(self):
|
|
check_support("APPO", {"num_workers": 1, "num_gpus": 0})
|
|
|
|
def testIMPALA(self):
|
|
check_support("IMPALA", {"num_workers": 1, "num_gpus": 0})
|
|
|
|
def testAPEX_DQN(self):
|
|
check_support(
|
|
"APEX", {
|
|
"num_workers": 2,
|
|
"learning_starts": 0,
|
|
"num_gpus": 0,
|
|
"min_iter_time_s": 1,
|
|
"timesteps_per_iteration": 100
|
|
})
|
|
|
|
|
|
if __name__ == "__main__":
|
|
import pytest
|
|
import sys
|
|
sys.exit(pytest.main(["-v", __file__]))
|