Merge pull request #177 from chainer/muupan-patch-3

Add docsting on eval_max_episode_len
chainer · Nov 22, 2017 · 1d0b27e · 1d0b27e
2 parents 041bfc8 + 736f1a6
commit 1d0b27e
Showing 1 changed file with 2 additions and 0 deletions.
diff --git a/chainerrl/experiments/train_agent.py b/chainerrl/experiments/train_agent.py
@@ -107,6 +107,8 @@ def train_agent_with_evaluation(
         max_episode_len (int): Maximum episode length.
         step_offset (int): Time step from which training starts.
         eval_explorer: Explorer used for evaluation.
+        eval_max_episode_len (int or None): Maximum episode length of
+            evaluation runs. If set to None, max_episode_len is used instead.
         eval_env: Environment used for evaluation.
         successful_score (float): Finish training if the mean score is greater
             or equal to this value if not None