diff --git a/rl_coach/agents/clipped_ppo_agent.py b/rl_coach/agents/clipped_ppo_agent.py
index 1a9d20216..f4933b724 100644
--- a/rl_coach/agents/clipped_ppo_agent.py
+++ b/rl_coach/agents/clipped_ppo_agent.py
@@ -329,6 +329,7 @@ def train(self):
             self.training_iteration += 1
             # should be done in order to update the data that has been accumulated * while not playing *
             self.update_log()
+            self.agent_logger.last_line_idx_written_to_csv -= 1
             return None
 
     def run_pre_network_filter_for_inference(self, state: StateType, update_internal_state: bool=False):