hucc/agents/hsd3.py [772:793]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        self._staging.put_row(d)
        self._cur_rewards.append(reward)

        if self._staging.size == self._staging.max:
            self._staging_to_buffer()

        self._n_steps += 1
        self._n_samples += done.nelement()
        self._n_samples_since_update += done.nelement()
        ilv = self._staging.interleave
        if self._buffer.size + self._staging.size - ilv < self._warmup_samples:
            return
        if self._n_samples_since_update >= self._samples_per_update:
            self.update()
            self._cur_rewards.clear()
            self._n_samples_since_update = 0

    def _staging_to_buffer(self):
        ilv = self._staging.interleave
        buf = self._staging
        assert buf._b is not None
        c = self._action_interval
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



hucc/agents/sachrl.py [270:291]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        self._staging.put_row(d)
        self._cur_rewards.append(reward)

        if self._staging.size == self._staging.max:
            self._staging_to_buffer()

        self._n_steps += 1
        self._n_samples += done.nelement()
        self._n_samples_since_update += done.nelement()
        ilv = self._staging.interleave
        if self._buffer.size + self._staging.size - ilv < self._warmup_samples:
            return
        if self._n_samples_since_update >= self._samples_per_update:
            self.update()
            self._cur_rewards.clear()
            self._n_samples_since_update = 0

    def _staging_to_buffer(self):
        ilv = self._staging.interleave
        buf = self._staging
        assert buf._b is not None
        c = self._action_interval
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -