Reinforcement Learning w/ Keras + OpenAI: Actor-Critic Models
Yash Patel
5018

Great article! simple implementation of DDPG.

BTW, is this a mistake?

line 145:

[what seems incorrect]

actor_target_weights = self.target_critic_model.get_weights()

[what I think is correct]

actor_target_weights = self.target_actor_model.get_weights()

One clap, two clap, three clap, forty?

By clapping more or less, you can signal to us which stories really stand out.