parser.add_argument('--ckpt_path',
type=str,
default="./ckpt",
help='if is test, must provide\
path where the trained ckpt file')
args = parser.parse_args()
set_seed(1)
if __name__ == "__main__":
context.set_context(mode=context.GRAPH_MODE,
device_target=args.device_target)
env = gym.make('CartPole-v1')
cfg.state_space_dim = env.observation_space.shape[0]
cfg.action_space_dim = env.action_space.n
agent = Agent(**cfg)
agent.load_dict()
for episode in range(300):
s0 = env.reset()
total_reward = 1
while True:
a0 = agent.act(s0)
s1, r1, done, _ = env.step(a0)
if done:
r1 = -1
agent.put(s0, a0, r1, s1)
if done:
break
