RL-PPO-Keras
RL-PPO-Keras copied to clipboard
found little fixes
Hi, yust went thru your code and found 2 little fixes: -if self.dic_agent_conf["OPTIMIZER"] is not "Adam" and RMSProp or fallback Adam are used, they didn't had an Loss defined -Entropy doesn't get calcualted over the percentage of one action, but rather over all percentages for all the different Actions Hope these little fixes can help you.