INNER CODE UNIT · Python

_learn

rasbt/machine-learning-book · ch19/cartpole/main.py:75

    def _learn(self, batch_samples):
        batch_states, batch_targets = [], []
        for transition in batch_samples:
            s, a, r, next_s, done = transition

            with torch.no_grad():
                if done:
                    target = r
                else:
                    pred = self.model(torch.tensor(next_s, dtype=torch.float32))[0]
                    target = r + self.gamma * pred.max()

                target_all = self.model(torch.tensor(s, dtype=torch.float32))[0]
                target_all[a] = target

            batch_states.append(s.flatten())
            batch_targets.append(target_all)
            self._adjust_epsilon()

View source record →