def test_a2c_exec_impl(self):
config = (
a2c.A2CConfig()
.environment(env="CartPole-v0")
.reporting(min_time_s_per_iteration=0)
)
for _ in framework_iterator(config):
trainer = config.build()
results = trainer.train()
check_train_results(results)
print(results)
check_compute_single_action(trainer)
trainer.stop()
def test_a2c_compilation(self):
"""Test whether an A2C can be built with both frameworks."""
config = a2c.A2CConfig().rollouts(num_rollout_workers=2, num_envs_per_worker=2)
num_iterations = 1
# Test against all frameworks.
for _ in framework_iterator(config, with_eager_tracing=True):
for env in ["CartPole-v0", "Pendulum-v1", "PongDeterministic-v0"]:
trainer = config.build(env=env)
for i in range(num_iterations):
results = trainer.train()
check_train_results(results)
print(results)
check_compute_single_action(trainer)
trainer.stop()
def _import_a2c():
import ray.rllib.algorithms.a2c as a2c
return a2c.A2C, a2c.A2CConfig().to_dict()