Method append_sample

1-grid-world/6-reinforce.py:76–79

(self, state, action, reward)

        return discounted

    def append_sample(self, state, action, reward):
        self.states.append(state)
        self.actions.append(action)
        self.rewards.append(reward)

    # Single gradient step using the whole episode.
    def train_model(self):