We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Hello,最近我在用NPU跑SAC时遇到了如题所说的情况,reward信息如下图。想请教一下PARL的同学这种情况可能是什么原因导致的呢? 我用GPU和CPU版本的Paddle试过,模型都能够正常训练,说明算法本身没有问题。我又统计了一下SAC用到的paddle算子,发现只有add clip full_ matmul relu scale tanh uniform,所以尝试了逐个把这些算子fallback到cpu上运行,但是除了屏蔽matmul外还是会出现相同的情况。而fallback matmul算子时在训练一段时间后会报如下的错误: 我这边暂时没有什么思路来定位问题了,恳请PARL的同学帮忙看一下,多谢! ps:使用的paddle和PARL都是最新的develop版本
add clip full_ matmul relu scale tanh uniform
The text was updated successfully, but these errors were encountered:
No branches or pull requests
Hello,最近我在用NPU跑SAC时遇到了如题所说的情况,reward信息如下图。想请教一下PARL的同学这种情况可能是什么原因导致的呢?
我用GPU和CPU版本的Paddle试过,模型都能够正常训练,说明算法本身没有问题。我又统计了一下SAC用到的paddle算子,发现只有
add clip full_ matmul relu scale tanh uniform
,所以尝试了逐个把这些算子fallback到cpu上运行,但是除了屏蔽matmul外还是会出现相同的情况。而fallback matmul算子时在训练一段时间后会报如下的错误:我这边暂时没有什么思路来定位问题了,恳请PARL的同学帮忙看一下,多谢!
ps:使用的paddle和PARL都是最新的develop版本
The text was updated successfully, but these errors were encountered: