Bo Zhou
Bo Zhou
It seems that you have installed two deep learning frameworks (torch & paddle). PARL supports these two frameworks, but it imports paddle by default. To specify torch as the backend...
Exactly. The commands related to `xparl` only launch a CPU cluster, and they will not change the number of actors used for training. Users must modify the `num_actors` in `main.py`...
hello,请问你有尝试py3.7吗？
也就是说3.7版本下GPU版本跑多趟的效果，都不如CPU吗？
example下提供的实验曲线都是在GPU上收集的，我怀疑是你的paddle-gpu版本安装有问题。 你有尝试过在paddle-gpu版本下运行过其他算法的训练吗？（比如CV、NLP）他们的运行结果正常吗？
了解，那我们这边重新测试下代码（GPU+py3.7）。
刚问了下团队的同学，目前我们正在升级mujoco环境（统一用deepmind收购后的版本），预计两周内发布新版本的代码。建议先使用CPU版本运行，GPU版本的我们后续也会同步测试效果并发布。
@rical730 Thank you so much for your contribution to our continuous integration process! Your work has been invaluable in improving PARL development workflow. We really appreciate your efforts.
自动同步，每次启动程序前会重新分发的。
The error message shows that you have not yet installed any deep learning framework. Please install PaddlePaddle before running the training script.