agent processor tests

ml-agents/mlagents/trainers/tests/test_agent_processor.py

     )
 
     fake_action_outputs = {
-        "action": [0.1, 0.1],
+        "action": {"continuous_action": [0.1, 0.1]},
-        "log_probs": [0.1, 0.1],
+        "log_probs": {"continuous_log_probs": [0.1, 0.1]},
     }
     mock_decision_steps, mock_terminal_steps = mb.create_mock_steps(
         num_agents=2,
     fake_action_info = ActionInfo(
-        action=[0.1, 0.1],
+        action={"continuous_action": [0.1, 0.1]},
         value=[0.1, 0.1],
         outputs=fake_action_outputs,
         agent_ids=mock_decision_steps.agent_id,
     )
 
     fake_action_outputs = {
-        "action": [0.1],
+        "action": {"continuous_action": [0.1]},
-        "log_probs": [0.1],
+        "log_probs": {"continuous_log_probs": [0.1]},
     }
     mock_decision_step, mock_terminal_step = mb.create_mock_steps(
         num_agents=1,
         done=True,
     )
     fake_action_info = ActionInfo(
-        action=[0.1],
+        action={"continuous_action": [0.1]},
         value=[0.1],
         outputs=fake_action_outputs,
         agent_ids=mock_decision_step.agent_id,
             processor.add_experiences(
                 mock_decision_step, mock_terminal_step, _ep, fake_action_info
             )
-            add_calls.append(mock.call([get_global_agent_id(_ep, 0)], [0.1]))
+            add_calls.append(
+                mock.call([get_global_agent_id(_ep, 0)], {"continuous_action": [0.1]})
+            )
         processor.add_experiences(
             mock_done_decision_step, mock_done_terminal_step, _ep, fake_action_info
         )
     )
 
     fake_action_outputs = {
-        "action": [0.1],
+        "action": {"continuous_action": [0.1]},
-        "log_probs": [0.1],
+        "log_probs": {"continuous_log_probs": [0.1]},
     }
     mock_decision_step, mock_terminal_step = mb.create_mock_steps(
         num_agents=1,
     fake_action_info = ActionInfo(
-        action=[0.1],
+        action={"continuous_action": [0.1]},
         value=[0.1],
         outputs=fake_action_outputs,
         agent_ids=mock_decision_step.agent_id,