Merge pull request #41 from The-Bread/master

Fix for RuntimeError for Environments with single continuous actions.

PPO.py

@@ -119,13 +119,18 @@ def evaluate(self, state, action):
 
         if self.has_continuous_action_space:
             action_mean = self.actor(state)
+
             action_var = self.action_var.expand_as(action_mean)
             cov_mat = torch.diag_embed(action_var).to(device)
             dist = MultivariateNormal(action_mean, cov_mat)
+
+            # For Single Action Environments.
+            if self.action_dim == 1:
+                action = action.reshape(-1, self.action_dim)
+
         else:
             action_probs = self.actor(state)
             dist = Categorical(action_probs)
-
         action_logprobs = dist.log_prob(action)
         dist_entropy = dist.entropy()
         state_values = self.critic(state)