def _check_environment_trains(env,
config,
meta_curriculum=None,
success_threshold=0.99):
# Create controller and begin training.
with tempfile.TemporaryDirectory() as dir:
run_id = "id"
save_freq = 99999
seed = 1337
StatsReporter.writers.clear(
) # Clear StatsReporters so we don't write to file
trainer_config = yaml.safe_load(config)
env_manager = SimpleEnvManager(env, FloatPropertiesChannel())
trainer_factory = TrainerFactory(
trainer_config=trainer_config,
summaries_dir=dir,
run_id=run_id,
model_path=dir,
keep_checkpoints=1,
train_model=True,
load_model=False,
seed=seed,
meta_curriculum=meta_curriculum,
multi_gpu=False,
)
tc = TrainerController(
trainer_factory=trainer_factory,
summaries_dir=dir,
model_path=dir,
run_id=run_id,
meta_curriculum=meta_curriculum,
train=True,
training_seed=seed,
sampler_manager=SamplerManager(None),
resampling_interval=None,
save_freq=save_freq,
)
# Begin training
tc.start_learning(env_manager)
print(tc._get_measure_vals())
if (success_threshold is not None
): # For tests where we are just checking setup and not reward
for mean_reward in tc._get_measure_vals().values():
assert not math.isnan(mean_reward)
assert mean_reward > success_threshold
def _check_environment_trains(env, config):
# Create controller and begin training.
with tempfile.TemporaryDirectory() as dir:
run_id = "id"
save_freq = 99999
seed = 1337
trainer_config = yaml.safe_load(config)
env_manager = SimpleEnvManager(env)
trainer_factory = TrainerFactory(
trainer_config=trainer_config,
summaries_dir=dir,
run_id=run_id,
model_path=dir,
keep_checkpoints=1,
train_model=True,
load_model=False,
seed=seed,
meta_curriculum=None,
multi_gpu=False,
)
tc = TrainerController(
trainer_factory=trainer_factory,
summaries_dir=dir,
model_path=dir,
run_id=run_id,
meta_curriculum=None,
train=True,
training_seed=seed,
fast_simulation=True,
sampler_manager=SamplerManager(None),
resampling_interval=None,
save_freq=save_freq,
)
# Begin training
tc.start_learning(env_manager)
print(tc._get_measure_vals())
for brain_name, mean_reward in tc._get_measure_vals().items():
assert not math.isnan(mean_reward)
assert mean_reward > 0.99
def test_simple():
config = """
default:
trainer: ppo
batch_size: 16
beta: 5.0e-3
buffer_size: 64
epsilon: 0.2
hidden_units: 128
lambd: 0.95
learning_rate: 5.0e-3
max_steps: 2500
memory_size: 256
normalize: false
num_epoch: 3
num_layers: 2
time_horizon: 64
sequence_length: 64
summary_freq: 500
use_recurrent: false
reward_signals:
extrinsic:
strength: 1.0
gamma: 0.99
"""
# Create controller and begin training.
with tempfile.TemporaryDirectory() as dir:
run_id = "id"
save_freq = 99999
tc = TrainerController(
dir,
dir,
run_id,
save_freq,
meta_curriculum=None,
load=False,
train=True,
keep_checkpoints=1,
lesson=None,
training_seed=1337,
fast_simulation=True,
sampler_manager=SamplerManager(None),
resampling_interval=None,
)
# Begin training
env = Simple1DEnvironment()
env_manager = SimpleEnvManager(env)
trainer_config = yaml.safe_load(config)
tc.start_learning(env_manager, trainer_config)
for brain_name, mean_reward in tc._get_measure_vals().items():
assert not math.isnan(mean_reward)
assert mean_reward > 0.99
