close the RECAP critic-policy loop

tests/test_tokenizer.py

@@ -37,6 +37,28 @@ def test_omitted_advantage_is_absent_not_a_third_condition_token() -> None:
     assert tokenizer.ADVANTAGE_NEGATIVE not in sequence.input_ids
 
 
+def test_value_input_does_not_encode_experience_outcome() -> None:
+    tokenizer = MiniTokenizer()
+    history = torch.zeros(8, 2)
+    value_input = tokenizer.build_value_input(history)
+
+    assert tokenizer.METADATA_DEMO not in value_input
+    assert tokenizer.METADATA_UNDERSTEER not in value_input
+    assert tokenizer.METADATA_STOP not in value_input
+    assert tokenizer.METADATA_INTERVENTION not in value_input
+
+
+def test_predicted_subtask_can_be_connected_to_action_condition() -> None:
+    tokenizer = MiniTokenizer()
+    history = torch.zeros(8, 2)
+    predicted = tokenizer.subtasks.encode("steer_left")
+    condition = tokenizer.build_action_condition(history, predicted, "positive")
+
+    assert condition[-2].item() == predicted
+    assert condition[-1].item() == tokenizer.ADVANTAGE_POSITIVE
+    assert tokenizer.ACTION_START not in condition
+
+
 def test_labels_predict_subtask_and_fast_but_not_external_advantage() -> None:
     tokenizer = MiniTokenizer()
     positive = tokenizer.build_policy_sequence(