def read_proto(filename):
results = results_pb2.MethodResult()
with open(filename, 'rb') as f:
results.ParseFromString(f.read())
return results
FLAGS = parser.parse_args()
def set_global_seed(seed):
tf.set_random_seed(seed)
np.random.seed(seed)
if __name__ == "__main__":
env_name = FLAGS.env_name
env = gym.make(env_name)
env.seed(FLAGS.seed)
set_global_seed(FLAGS.seed)
print(FLAGS)
results = results_pb2.MethodResult()
# setting evaluation policy
if FLAGS.pi == 4:
pi = GaussianPolicy(env.observation_space,
env.action_space,
scope='pi',
train_type='reinforce',
hidden_sizes=[64, 64],
act_fn=tf.nn.tanh)
#pi = GaussianPolicy(env.observation_space, env.action_space, scope='pi', train_type = 'reinforce', hidden_sizes = [16, 16])
pi.load_policy(FLAGS.pi_weightfile)
# setting behavior policy
if FLAGS.pi_b == 4:
pi_b = pi