prev_snapshot_dir = logger.get_snapshot_dir()
prev_mode = logger.get_snapshot_mode()
logger.set_snapshot_dir(log_dir)
logger.set_snapshot_mode("gaplast")
logger.set_snapshot_gap(100)
logger.set_log_tabular_only(False)
logger.push_prefix("[%s] " % "FixMapStartState")
from Algo import parallel_sampler
parallel_sampler.initialize(n_parallel=1)
parallel_sampler.set_seed(0)
policy = CategoricalConvPolicy(
env_spec=env.spec,
name="ConvNet",
conv_filters=[3, 3, 3, 3],
conv_filter_sizes=[3, 5, 3, 3],
conv_strides=[1, 1, 1, 1],
conv_pads=['SAME', 'SAME', 'SAME', 'SAME'],
)
baseline = LinearFeatureBaseline(env_spec=env.spec)
with tf.Session() as sess:
algo = VPG_t(
env=env,
policy=policy,
baseline=baseline,
batch_size=2048,
max_path_length=env._wrapped_env.params['traj_limit'],
n_itr=20000,