TypeError: not a sequence

运行程序：
args=Arguments(if_on_policy=False)
args.agent=AgentDDPG()
env=gym.make('Pendulum-v0')
env.target_reward=-200
args.env=PreprocessEnv(env=env)
args.reward_scale=2**-3
args.net_dim=2**7
args.batch_size=2**7

train_and_evaluate(args)
发生错误：
File "F:/engine_research_20210901/ElegantRL/ElegantRL-master/elegantrl/run.py", line 717, in demo_continuous_action
train_and_evaluate(args)
File "F:/engine_research_20210901/ElegantRL/ElegantRL-master/elegantrl/run.py", line 190, in train_and_evaluate
steps, r_exp = update_buffer(trajectory)
File "F:/engine_research_20210901/ElegantRL/ElegantRL-master/elegantrl/run.py", line 172, in update_buffer
ary_other = torch.as_tensor([item[1] for item in _trajectory])
TypeError: not a sequence