src_code/learners/q_explore_learner.py [175:207]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            self.logger.log_stat("grad_norm", grad_norm, t_env)
            mask_elems = mask.sum().item()
            self.logger.log_stat("td_error_abs", (masked_td_error.abs().sum().item()/mask_elems), t_env)
            self.logger.log_stat("q_taken_mean", (chosen_action_qvals * mask).sum().item()/(mask_elems * self.args.n_agents), t_env)
            self.logger.log_stat("target_mean", (targets * mask).sum().item()/(mask_elems * self.args.n_agents), t_env)
            self.log_stats_t = t_env

    def _update_targets(self):
        self.target_mac.load_state(self.mac)
        if self.mixer is not None:
            self.target_mixer.load_state_dict(self.mixer.state_dict())
        self.logger.console_logger.info("Updated target network")

    def cuda(self):
        self.mac.cuda()
        self.target_mac.cuda()
        if self.mixer is not None:
            self.mixer.cuda()
            self.target_mixer.cuda()

    def save_models(self, path):
        self.mac.save_models(path)
        if self.mixer is not None:
            th.save(self.mixer.state_dict(), "{}/mixer.th".format(path))
        th.save(self.optimiser.state_dict(), "{}/opt.th".format(path))

    def load_models(self, path):
        self.mac.load_models(path)
        # Not quite right but I don't want to save target networks
        self.target_mac.load_models(path)
        if self.mixer is not None:
            self.mixer.load_state_dict(th.load("{}/mixer.th".format(path), map_location=lambda storage, loc: storage))
        self.optimiser.load_state_dict(th.load("{}/opt.th".format(path), map_location=lambda storage, loc: storage))
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



src_code/learners/q_influence_learner.py [134:166]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            self.logger.log_stat("grad_norm", grad_norm, t_env)
            mask_elems = mask.sum().item()
            self.logger.log_stat("td_error_abs", (masked_td_error.abs().sum().item()/mask_elems), t_env)
            self.logger.log_stat("q_taken_mean", (chosen_action_qvals * mask).sum().item()/(mask_elems * self.args.n_agents), t_env)
            self.logger.log_stat("target_mean", (targets * mask).sum().item()/(mask_elems * self.args.n_agents), t_env)
            self.log_stats_t = t_env

    def _update_targets(self):
        self.target_mac.load_state(self.mac)
        if self.mixer is not None:
            self.target_mixer.load_state_dict(self.mixer.state_dict())
        self.logger.console_logger.info("Updated target network")

    def cuda(self):
        self.mac.cuda()
        self.target_mac.cuda()
        if self.mixer is not None:
            self.mixer.cuda()
            self.target_mixer.cuda()

    def save_models(self, path):
        self.mac.save_models(path)
        if self.mixer is not None:
            th.save(self.mixer.state_dict(), "{}/mixer.th".format(path))
        th.save(self.optimiser.state_dict(), "{}/opt.th".format(path))

    def load_models(self, path):
        self.mac.load_models(path)
        # Not quite right but I don't want to save target networks
        self.target_mac.load_models(path)
        if self.mixer is not None:
            self.mixer.load_state_dict(th.load("{}/mixer.th".format(path), map_location=lambda storage, loc: storage))
        self.optimiser.load_state_dict(th.load("{}/opt.th".format(path), map_location=lambda storage, loc: storage))
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -