Fix 0.4.0 related issues

Author: ikostrikov2

my_optim.py

@@ -62,8 +62,8 @@ def step(self, closure=None):
 
                 denom = exp_avg_sq.sqrt().add_(group['eps'])
 
-                bias_correction1 = 1 - beta1**state['step'][0]
-                bias_correction2 = 1 - beta2**state['step'][0]
+                bias_correction1 = 1 - beta1 ** state['step'].item()
+                bias_correction2 = 1 - beta2 ** state['step'].item()
                 step_size = group['lr'] * math.sqrt(
                     bias_correction2) / bias_correction1
 

train.py

@@ -57,7 +57,7 @@ def train(rank, args, shared_model, counter, lock, optimizer=None):
             entropy = -(log_prob * prob).sum(1, keepdim=True)
             entropies.append(entropy)
 
-            action = prob.multinomial().data
+            action = prob.multinomial(num_samples=1).data
             log_prob = log_prob.gather(1, Variable(action))
 
             state, reward, done, _ = env.step(action.numpy())