PLR setup but slow

CarperAI · Nov 8, 2024 · 2aa6ad6 · 2aa6ad6
1 parent f9db936
commit 2aa6ad6
Show file tree

Hide file tree

Showing 2 changed files with 3 additions and 1 deletion.
diff --git a/reinforcement_learning/clean_pufferl.py b/reinforcement_learning/clean_pufferl.py
@@ -313,7 +313,7 @@ def evaluate(data):
                     next_lstm_state[0][:, env_id],
                     next_lstm_state[1][:, env_id],
                 )
-
+            print("puffer shape", o.shape)
             actions, logprob, value, next_lstm_state = data.policy_pool.forwards(
                 o.to(data.device), next_lstm_state
             )

diff --git a/syllabus_wrapper.py b/syllabus_wrapper.py
@@ -105,6 +105,8 @@ def _prepare_state(self, state):
             new_state.append(np.stack(padded_obs.values()))
 
         state = torch.Tensor(np.stack(new_state)).to(self.device)
+        print("syllabus shape", state.shape)
+
         return state
 
     def _set_eval_mode(self):