Syk-yr

谢谢作者的解答，我训练SAC时已经运行了将近4.49e+04步才报的错，不过也很奇怪我训练了三次，有两次在4.49e+04步报的错，另一次在4.39e+04报的错？下面函数找leaf_id 中深度的循环少一层，好像与莫凡的代码有点区别，不知道是不是我理解有误？ ```python def get_leaf_id_and_value(self, v) -> Tuple[int, float]: """Tree structure and array storage: Tree index: 0 -> storing priority sum | | 1 2 | | | | 3...

您好，我将我的ReplayBuffer的最大容量改为了10**6。

> Anyone encountering a situation where the GPU memory is insufficient can reduce memory usage significantly by using the command model = torch.compile(model). In my experimental setup, this approach reduced...

> > > Anyone encountering a situation where the GPU memory is insufficient can reduce memory usage significantly by using the command model = torch.compile(model). In my experimental setup, this...

> > "I am currently using PyTorch version 2.1.0 (with CUDA 11.8 support) and PyTorch Lightning version 2.1.2. I've encountered an issue related to 'self.log' conflicts. A similar issue has...

> > I also added this line of code where you mentioned it, but it still reported an error：raise TypeError(f"Trainer.fit() requires a LightningModule, got: {model.class.qualname}") TypeError: Trainer.fit() requires a LightningModule,...