From 4c4216802316bae80852df55998fddb87e71e2d3 Mon Sep 17 00:00:00 2001 From: Deric Pang Date: Thu, 6 Sep 2018 17:13:38 -0700 Subject: [PATCH] Fix bug when academy max steps is set to nonzero value. --- ml-agents/mlagents/trainers/trainer_controller.py | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/ml-agents/mlagents/trainers/trainer_controller.py b/ml-agents/mlagents/trainers/trainer_controller.py index be53dcee89..b4d2e4f854 100644 --- a/ml-agents/mlagents/trainers/trainer_controller.py +++ b/ml-agents/mlagents/trainers/trainer_controller.py @@ -336,14 +336,17 @@ def start_learning(self): # If any lessons were incremented or the environment is # ready to be reset if (self.meta_curriculum - and any(lessons_incremented.values()) - or self.env.global_done): + and any(lessons_incremented.values())): curr_info = self._reset_env() for brain_name, trainer in self.trainers.items(): trainer.end_episode() for brain_name, changed in lessons_incremented.items(): if changed: self.trainers[brain_name].reward_buffer.clear() + elif self.env.global_done: + curr_info = self._reset_env() + for brain_name, trainer in self.trainers.items(): + trainer.end_episode() # Decide and take an action take_action_vector, \