def step(self, action):
        ... #the very end of my step function
        if self._agent_selector.is_last():
            self._accumulate_rewards() #global rewards are definitely updated
            self._clear_rewards()

        self.agent_selection = self._agent_selector.next()

def reward_metric(rews):
    return rews[:, 0] #shape of rews is correct, but rews[:, 1] is always 0

def _get_agents(...):
    ...
    if agent1 is None:
        net = Net(
            state_shape=observation_space.shape or observation_space.n,
            action_shape=env.action_space.shape or env.action_space.n,
            hidden_sizes=args.hidden_sizes,
            softmax=True,
            num_atoms=51,
            dueling_param=({
                "linear_layer": noisy_linear
            }, {
                "linear_layer": noisy_linear
            }),
            device=args.device,
        ).to(args.device)
        if optim is None:
            optim = torch.optim.Adam(net.parameters(), lr=args.lr)
        agent1 = RainbowPolicy(
            model=net,
            optim=optim,
            action_space=env.action_space,
            discount_factor=args.gamma,
            estimation_step=args.n_step,
            target_update_freq=args.target_update_freq,
        ).to(args.device)

        if (args.watch):
            agent1.load_state_dict(torch.load('./log/ttt/dqn/policy_0.pth'))

    if agent2 is None:
    
        agent2 = RainbowPolicy(
            model=net,
            optim=optim,
            action_space=env.action_space,
            discount_factor=args.gamma,
            estimation_step=args.n_step,
            target_update_freq=args.target_update_freq,
        ).to(args.device)

        if (args.watch):
            agent2.load_state_dict(torch.load('./log/ttt/dqn/policy_1.pth'))