Rao Xuan

是的，我在PEMS03数据集上跑了2次还是这个结果，是mxnet版本问题吗？我的是python3.6 mxnet 1.5.0 cuda version 11.2 。 我mxnet-cu100 mxnet-cu101 mxnet-cu102都试过了，在101版本运行成功，其他2个版本运行报错了，报错的问题也是与mxnet版本有关

这代码我有时候能运行，有时候报mxnet版本错误... val_loader.reset() prediction = mod.predict(val_loader)[1].asnumpy() loss = masked_mae_np(val_y, prediction, 0) 想问个问题，之前在处理数据时是把训练集，测试集，验证集的输入X归一化处理，而标签Y没有归一化处理， prediction = mod.predict(val_loader)[1].asnumpy()这部分预测出来的值应该要逆归一化，也就是重新变成流量值才能和Y计算MAE吧？请问这个逆归一化处理在哪里呢？

我在debug的时候经常遇到[01:04:15] c:\jenkins\workspace\mxnet-tag\mxnet\src\operator\linalg_impl.h:213: Check failed: e == CUBLAS_STATUS_SUCCESS (13 vs. 0) : cuBLAS: CUBLAS_STATUS_EXECUTION_FAILED错误。 for idx, databatch in enumerate(train_loader): mod.forward_backward(databatch) mod.update_metric(metric, databatch.label) mod.update() 是因为这个错误导致 mod.update_metric(metric, databatch.label)这一行的mxnet内部所预测出的preds结果全是0吗？

Thanks for your reply! Could you please tell about the machine you used in the experiment? We use Intel XEON 4210R CPU and RTX 3090 GPU, the main time consumption...

@weixiang-smart @jianingq , I modify `action = act_result.action to action = act_result.action.cpu().numpy()` but still encounter "RuntimeError: Attempted to send CUDA tensor received from another process; this is not currently supported....

The error happens when collecting new transitions, so it is not about the training process. Therefore, for example, consider a [BCAgent](https://github.com/stepjam/ARM/blob/main/arm/baselines/bc/bc_agent.py#L32), I check the code again and find that the...

@yananliusdu you can try the above [method](https://github.com/stepjam/ARM/issues/8#issuecomment-1369506544)

"loss, h = trainer.loss(x, t, s, y, y_t, y_s, h, active_users)" in train.py I try to delete the hidden state output "h", the code could run normally. My environment is...