the worker can't forward in Actor-network

[jiameij]

Thanks for your share!
i run this code using env-id:Walker2d-v2, num_of_workers: 2
however, it seems that the worker can't forward in Actor-network, and it shows no error, it just in running state and can't get results
model.py
def __call__(self, *input, **kwargs): for hook in self._forward_pre_hooks.values(): hook(self, input) if torch.jit._tracing: result = self._slow_forward(*input, **kwargs) else: result = self.forward(*input, **kwargs) for hook in self._forward_hooks.values(): hook_result = hook(self, input, result) if hook_result is not None: raise RuntimeError( "forward hooks should never return any values, but '{}'" "didn't return None".format(hook)) if len(self._backward_hooks) > 0: var = result while not isinstance(var, torch.Tensor): if isinstance(var, dict): var = next((v for v in var.values() if isinstance(v, torch.Tensor))) else: var = var[0] grad_fn = var.grad_fn if grad_fn is not None: for hook in self._backward_hooks.values(): wrapper = functools.partial(hook, self) functools.update_wrapper(wrapper, hook) grad_fn.register_hook(wrapper) return result
it is my first time to use multiprocessing, i do't know what's wrong with it.
thank you for your help

[TianhongDai]

@jiameij Sorry for reply so late, it's the problem of thread blocking. I have solved that, need to add the os.environ['OMP_NUM_THREADS'] = '1'. I will revise it to pytorch-0.4.1 in the next few weeks. Hope this can help you.

[jiameij]

@TianhongDai thank you for your help!