JieMEI1994

Why use self.batch_size instead of batch_size

1

From reinforcement-learning/2-cartpole/1-dqn/cartpole_dqn.py/train_model def train_model(self): if len(self.memory) < self.train_start: return batch_size = min(self.batch_size, len(self.memory)) mini_batch = random.sample(self.memory, batch_size) update_input = np.zeros((batch_size, self.state_size)) update_target = np.zeros((batch_size, self.state_size)) action, reward, done = [],...

About the Learning Performance

6

Thanks for your code and description. It help a lot to understand the DQN algorithm, but my code can not gain the learning performance as good as yours. I wonder...