Bug in RL/Policy_Gradient/RL_brain.py

princewen / tensorflow_practice

tensorflow实战练习，包括强化学习、推荐系统、nlp等

6.72k stars 3.28k forks source link

Bug in RL/Policy_Gradient/RL_brain.py #54

Closed RukawaKaede closed 4 years ago

RukawaKaede commented 4 years ago

Hi! Thank you for your contribution. I think the 'all_act' in this line should be 'self.all_act_prob'. Please correct me if I was wrong! line 78 in RL_brain.py