diff --git a/environment_wrapper.py b/environment_wrapper.py index f624a2132529e8b87ba554a00376ba9a77fb6285..19e6cb0166e73c5ddbc4cb893258845720a77c21 100644 --- a/environment_wrapper.py +++ b/environment_wrapper.py @@ -34,8 +34,6 @@ def one_episode(environment, agent, render, learn, max_steps=3000): if learn: agent.learn() if done: - if learn: - agent.learn(offline=True) break return score