minihack/agent/polybeast/models/base.py [64:90]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        return glyphs, features

    def embed_state(self, inputs):
        raise NotImplementedError

    @torch.no_grad()
    def update_running_moments(self, reward_batch):
        """Maintains a running mean of reward."""
        new_count = len(reward_batch)
        new_sum = torch.sum(reward_batch)
        new_mean = new_sum / new_count

        curr_mean = self.reward_sum / self.reward_count
        new_m2 = torch.sum((reward_batch - new_mean) ** 2) + (
            (self.reward_count * new_count)
            / (self.reward_count + new_count)
            * (new_mean - curr_mean) ** 2
        )

        self.reward_count += new_count
        self.reward_sum += new_sum
        self.reward_m2 += new_m2

    @torch.no_grad()
    def get_running_std(self):
        """Returns standard deviation of the running mean of the reward."""
        return torch.sqrt(self.reward_m2 / self.reward_count)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



minihack/agent/rllib/models.py [94:120]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        return glyphs, features

    def embed_state(self, inputs):
        raise NotImplementedError

    @torch.no_grad()
    def update_running_moments(self, reward_batch):
        """Maintains a running mean of reward."""
        new_count = len(reward_batch)
        new_sum = torch.sum(reward_batch)
        new_mean = new_sum / new_count

        curr_mean = self.reward_sum / self.reward_count
        new_m2 = torch.sum((reward_batch - new_mean) ** 2) + (
            (self.reward_count * new_count)
            / (self.reward_count + new_count)
            * (new_mean - curr_mean) ** 2
        )

        self.reward_count += new_count
        self.reward_sum += new_sum
        self.reward_m2 += new_m2

    @torch.no_grad()
    def get_running_std(self):
        """Returns standard deviation of the running mean of the reward."""
        return torch.sqrt(self.reward_m2 / self.reward_count)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -