def make_configs(self):
config = Config()
config.add_item(name='iter', val=30)
config.add_item(name='hidden_sizes', val=[64, 32, 16])
config.add_random_eps(name='lr', base=10, low=-6, high=0, num_sample=10)
config.add_random_continuous(name='values', low=-5, high=5, num_sample=5)
config.add_random_discrete(name='select', list_val=[43223, 5434, 21314], num_sample=10, replace=True)
configs = config.make_configs()
return configs
def make_configs(self):
config = Config()
config.add_grid(name='use_ConvVAE', val=[True, False])
config.add_item(name='num_epochs', val=100)
config.add_item(name='cuda', val=True)
config.add_item(name='seed', val=1)
config.add_item(name='batch_size', val=128)
config.add_item(name='log_interval', val=100)
configs = config.make_configs()
return configs
def test_config():
config = Config()
config.add_item(name='algo', val='RL')
config.add_item(name='iter', val=30)
config.add_item(name='hidden_sizes', val=[64, 32, 16])
config.add_grid(name='cuda_num', val=[1, 2, 3])
config.add_random_eps(name='lr', base=10, low=-6, high=0, num_sample=10)
config.add_random_continuous(name='values', low=-5, high=5, num_sample=5)
config.add_random_discrete(name='select',
list_val=[43223, 5434, 21314],
num_sample=10,
replace=True)
configs = config.make_configs()
assert len(configs) == 1500
assert np.alltrue([config['ID'] == i for i, config in enumerate(configs)])
assert np.alltrue([config['algo'] == 'RL' for config in configs])
assert np.alltrue(['iter' in config for config in configs])
assert np.alltrue(
[config['hidden_sizes'] == [64, 32, 16] for config in configs])
assert np.alltrue([config['cuda_num'] in [1, 2, 3] for config in configs])
assert np.alltrue(
[config['lr'] > 0 and config['lr'] < 1 for config in configs])
assert np.alltrue([
config['values'] >= -5 and config['values'] < 5 for config in configs
])
assert np.alltrue(
[config['select'] in [43223, 5434, 21314] for config in configs])
with pytest.raises(AssertionError):
config.add_grid(name='wrong', val='yes')
def make_configs(self):
config = Config()
# General configurations
config.add_item(name='cuda', val=True)
config.add_item(name='cuda_id', val=1)
# Random seeds
# Generated by: np.random.randint(0, np.iinfo(np.int32).max, 10)
config.add_grid(name='seed',
val=[
1284204222, 1079618558, 310837894, 1130644153,
2099771862, 1234806135, 92464293, 146053987,
1140885110, 988661500
])
# Algorithm configuration
config.add_item(name='algo:lr', val=1e-3)
config.add_item(name='algo:gamma', val=0.99)
config.add_item(name='algo:use_lr_scheduler', val=True)
config.add_item(name='env:id', val='CartPole-v1')
# Engine configuration
config.add_item(name='train:iter', val=4000)
config.add_item(name='train:N', val=1)
config.add_item(name='train:T', val=500)
config.add_item(name='eval:N', val=10)
config.add_item(name='eval:T', val=500)
# Agent configuration
config.add_grid(name='agent:standardize', val=[True, False])
config.add_item(name='agent:max_grad_norm',
val=0.5) # gradient clipping with max gradient norm
config.add_item(name='agent:value_coef',
val=0.5) # Coefficient for learning value function
config.add_item(name='agent:entropy_coef',
val=0.01) # Coefficient for maximize policy entropy
# Logging configurations
config.add_item(name='log:interval', val=100)
config.add_item(name='log:dir', val='logs')
configs = config.make_configs()
return configs
def make_configs(self):
config = Config()
config.add_grid(name='cuda', val=[True])
config.add_item(name='seed', val=1)
config.add_item(name='lr', val=1e-2)
config.add_item(name='gamma', val=0.995)
config.add_item(name='standardize_r', val=True)
config.add_item(name='train_iter', val=1000)
config.add_item(name='N', val=1)
config.add_item(name='T', val=300)
config.add_item(name='use_value', val=True) # True for actor-critic
config.add_item(name='entropy_coef', val=0.0)
config.add_item(name='value_coef', val=0.0)
config.add_item(name='max_grad_norm', val=None)
config.add_item(name='log_interval', val=100)
configs = config.make_configs()
return configs
