Gradients are none for the actor after calling loss.backward

reinforcement-learning
3

hi @TomH ,i have met the same problem with you .it can be found in here.https://discuss.pytorch.org/t/loss-not-converge-in-ddpg/191523/7?u=yxz77777
could you please give some advice to me ?
or can you show me about more details on your solution?