def extra_grad_info(self, train_batch): with torch.no_grad(): if stats_fn: stats_dict = stats_fn(self, train_batch) else: stats_dict = TorchPolicy.extra_grad_info(self, train_batch) return convert_to_non_torch_type(stats_dict)
def extra_grad_info(self, batch_tensors): if stats_fn: return stats_fn(self, batch_tensors) else: return TorchPolicy.extra_grad_info(self, batch_tensors)
def extra_grad_info(self, train_batch): if stats_fn: return stats_fn(self, train_batch) else: return TorchPolicy.extra_grad_info(self, train_batch)