LEI TAI
And you mentioned in https://github.com/muupan/async-rl/wiki They multiply the gradients of V by 0.5. So in the **a3c.py** there are the parameters (pi_loss_coef=1.0, v_loss_coef=0.5) But why there is another 0.5 in...
Sorry kilmarnock. I implement the dqn network in other environment but not the Atari game. So finally I did not use the SQL. Hope you have solved it successfully.
@w102060018w Would you mind explaining the final_masknp and gt_masknp more clearly? I added the final mask extracted from outputs ``` final_mask = outputs['mask']['mask'] ``` And I revised the code like...
@w102060018w I just found that correct bboxes with masks are shown on the image. The yellow bboxes are mismatch results.
FYI, 我的相关版本： Ipopt-3.12.13 CppAD-20190200.1 在我这运行没有问题，请注意你有没有给所有变量设置上下界
如果你可以搞成一个docker环境，并且复现相关问题的话 我可以帮你看一下
Check the **pytorch-rl/utils/options.py**. If your GPU is available, the repo will load your GPU defaultly Notice that A3C does not use GPU. To render the env, change the render in...
并不是很清楚具体需求: ### 1. 我们希望在学术项目中使用您的代码 请遵循[license](https://github.com/jingweiz/pytorch-dnc/blob/master/LICENSE.md), 并欢迎引用我们的相关论文 @article{zhang2017neural, title={Neural SLAM}, author={Zhang, Jingwei and Tai, Lei and Boedecker, Joschka and Burgard, Wolfram and Liu, Ming}, journal={arXiv preprint arXiv:1706.09520}, year={2017}} ### 2. 需要的功能是基于原有状态运行一步DNC，返回状态和输出...
I build a [pytorch version](https://github.com/onlytailei/carla_cil_pytorch) to train the policy in case that you may be interested.
Do you have mkl on the server?