def run_experiment_with_multiple_seeds(variant):
scores = []
for i in range(n_seeds):
variant['seed'] = str(int(variant['seed']) + i)
exp_prefix = variant['exp_prefix']
scores.append(
run_experiment_here(
get_ocm_score,
exp_prefix=exp_prefix,
variant=variant,
exp_id=i,
))
return np.mean(scores)
args_dict['run_experiment_kwargs']['variant']['rl_variant']['algo_kwargs'][
'base_kwargs']['num_epochs'] = 300
method_call = args_dict['method_call']
run_experiment_kwargs = args_dict['run_experiment_kwargs']
output_dir = args_dict['output_dir']
run_mode = args_dict.get('mode', None)
if run_mode and run_mode in ['slurm_singularity', 'sss']:
import os
run_experiment_kwargs['variant']['slurm-job-id'] = os.environ.get(
'SLURM_JOB_ID', None)
if run_mode and run_mode == 'ec2':
try:
import urllib.request
instance_id = urllib.request.urlopen(
'http://169.254.169.254/latest/meta-data/instance-id').read(
).decode()
run_experiment_kwargs['variant']['EC2_instance_id'] = instance_id
except Exception as e:
print("Could not get instance ID. Error was...")
print(e)
# Do this in case base_log_dir was already set
run_experiment_kwargs['base_log_dir'] = output_dir
run_experiment_here(method_call,
include_exp_prefix_sub_dir=False,
**run_experiment_kwargs)
else:
run_experiment_here(method_call,
log_dir=output_dir,
**run_experiment_kwargs)
def example(*_):
env = HalfCheetahEnv()
es = OUStrategy(env_spec=env.spec)
qf = FeedForwardCritic(
name_or_scope="critic",
env_spec=env.spec,
)
policy = FeedForwardPolicy(
name_or_scope="actor",
env_spec=env.spec,
)
algorithm = DDPG(
env,
es,
policy,
qf,
n_epochs=25,
batch_size=1024,
replay_pool_size=10000,
)
algorithm.train()
if __name__ == "__main__":
run_experiment_here(
example,
exp_prefix="ddpg-half-cheetah",
seed=2,
)
max_path_length=max_path_length,
# qf_learning_rate=1e-1,
# policy_learning_rate=1e-1,
)
variant = dict(
H=H,
num_values=num_values,
exp_prefix=exp_prefix,
ddpg_params=ddpg_params,
)
for seed in range(n_seeds):
variant['seed'] = seed
variant['exp_id'] = exp_id
if USE_EC2:
run_experiment(
run_linear_ocm_exp,
exp_prefix=exp_prefix,
seed=seed,
mode="ec2",
variant=variant,
)
else:
run_experiment_here(
run_linear_ocm_exp,
exp_prefix=exp_prefix,
variant=variant,
exp_id=exp_id,
seed=seed,
)