e767de044b
* remove dummy net; delete two files * split code to have backbone and head * rename class * change torch.float to torch.float32 * use flatten(1) instead of view(batch, -1) * remove dummy net in docs * bugfix for rnn * fix cuda error * minor fix of docs * do not change the example code in dqn tutorial, since it is for demonstration Co-authored-by: Trinkle23897 <463003665@qq.com>