Method push

examples/reinforcement_learning/tutorial_SAC.py:97–101

(self, state, action, reward, next_state, done)

        self.position = 0

    def push(self, state, action, reward, next_state, done):
        if len(self.buffer) < self.capacity:
            self.buffer.append(None)
        self.buffer[self.position] = (state, action, reward, next_state, done)
        self.position = int((self.position + 1) % self.capacity)  # as a ring buffer

    def sample(self, BATCH_SIZE):
        batch = random.sample(self.buffer, BATCH_SIZE)