跑了一千多次报错

[zhian17]

Traceback (most recent call last):
File "legged_gym/scripts/train.py", line 23, in
train(args)
File "legged_gym/scripts/train.py", line 18, in train
ppo_runner.learn(num_learning_iterations=train_cfg.runner.max_iterations, init_at_random_ep_len=True)
File "/home/xjzz/rsl_rl/rsl_rl/runners/on_policy_runner.py", line 132, in learn
mean_value_loss, mean_surrogate_loss = self.alg.update()
File "/home/xjzz/rsl_rl/rsl_rl/algorithms/ppo.py", line 131, in update
self.actor_critic.act(obs_batch, masks=masks_batch, hidden_states=hid_states_batch[0])
File "/home/xjzz/rsl_rl/rsl_rl/modules/actor_critic_recurrent.py", line 77, in act
input_a = self.memory_a(observations, masks, hidden_states)
File "/home/xjzz/anaconda3/envs/rl/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1532, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/home/xjzz/anaconda3/envs/rl/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1541, in _call_impl
return forward_call(*args, **kwargs)
File "/home/xjzz/rsl_rl/rsl_rl/modules/actor_critic_recurrent.py", line 107, in forward
out = unpad_trajectories(out, masks)
File "/home/xjzz/rsl_rl/rsl_rl/utils/utils.py", line 71, in unpad_trajectories
return trajectories.transpose(1, 0)[masks.transpose(1, 0)].view(-1, trajectories.shape[0], trajectories.shape[-1]).transpose(1, 0)
IndexError: The shape of the mask [2009, 24] at index 1 does not match the shape of the indexed tensor [2009, 20, 64] at index 1

没找到解决方法，有大佬会吗