src_code/learners/q_explore_learner.py [83:129]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    def train(self, batch: EpisodeBatch, t_env: int, episode_num: int):
        # Get the relevant quantities
        rewards = batch["reward"][:, :-1]
        actions = batch["actions"][:, :-1]
        terminated = batch["terminated"][:, :-1].float()
        mask = batch["filled"][:, :-1].float()
        mask[:, 1:] = mask[:, 1:] * (1 - terminated[:, :-1])
        avail_actions = batch["avail_actions"]

        # Calculate estimated Q-Values
        mac_out = []
        self.mac.init_hidden(batch.batch_size)
        for t in range(batch.max_seq_length):
            agent_outs = self.mac.forward(batch, t=t)
            mac_out.append(agent_outs)
        mac_out = th.stack(mac_out, dim=1)  # Concat over time

        # Pick the Q-Values for the actions taken by each agent
        chosen_action_qvals = th.gather(mac_out[:, :-1], dim=3, index=actions).squeeze(3)  # Remove the last dim

        # Calculate the Q-Values necessary for the target
        target_mac_out = []
        self.target_mac.init_hidden(batch.batch_size)
        for t in range(batch.max_seq_length):
            target_agent_outs = self.target_mac.forward(batch, t=t)
            target_mac_out.append(target_agent_outs)

        # We don't need the first timesteps Q-Value estimate for calculating targets
        target_mac_out = th.stack(target_mac_out[1:], dim=1)  # Concat across time

        # Mask out unavailable actions
        target_mac_out[avail_actions[:, 1:] == 0] = -9999999

        # Max over target Q-Values
        if self.args.double_q:
            # Get actions that maximise live Q (for double q-learning)
            mac_out_detach = mac_out.clone().detach()
            mac_out_detach[avail_actions == 0] = -9999999
            cur_max_actions = mac_out_detach[:, 1:].max(dim=3, keepdim=True)[1]
            target_max_qvals = th.gather(target_mac_out, 3, cur_max_actions).squeeze(3)
        else:
            target_max_qvals = target_mac_out.max(dim=3)[0]

        # Mix
        if self.mixer is not None:
            chosen_action_qvals = self.mixer(chosen_action_qvals, batch["state"][:, :-1])
            target_max_qvals = self.target_mixer(target_max_qvals, batch["state"][:, 1:])
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



src_code/learners/q_influence_learner.py [43:89]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    def train(self, batch: EpisodeBatch, t_env: int, episode_num: int):
        # Get the relevant quantities
        rewards = batch["reward"][:, :-1]
        actions = batch["actions"][:, :-1]
        terminated = batch["terminated"][:, :-1].float()
        mask = batch["filled"][:, :-1].float()
        mask[:, 1:] = mask[:, 1:] * (1 - terminated[:, :-1])
        avail_actions = batch["avail_actions"]

        # Calculate estimated Q-Values
        mac_out = []
        self.mac.init_hidden(batch.batch_size)
        for t in range(batch.max_seq_length):
            agent_outs = self.mac.forward(batch, t=t)
            mac_out.append(agent_outs)
        mac_out = th.stack(mac_out, dim=1)  # Concat over time

        # Pick the Q-Values for the actions taken by each agent
        chosen_action_qvals = th.gather(mac_out[:, :-1], dim=3, index=actions).squeeze(3)  # Remove the last dim

        # Calculate the Q-Values necessary for the target
        target_mac_out = []
        self.target_mac.init_hidden(batch.batch_size)
        for t in range(batch.max_seq_length):
            target_agent_outs = self.target_mac.forward(batch, t=t)
            target_mac_out.append(target_agent_outs)

        # We don't need the first timesteps Q-Value estimate for calculating targets
        target_mac_out = th.stack(target_mac_out[1:], dim=1)  # Concat across time

        # Mask out unavailable actions
        target_mac_out[avail_actions[:, 1:] == 0] = -9999999

        # Max over target Q-Values
        if self.args.double_q:
            # Get actions that maximise live Q (for double q-learning)
            mac_out_detach = mac_out.clone().detach()
            mac_out_detach[avail_actions == 0] = -9999999
            cur_max_actions = mac_out_detach[:, 1:].max(dim=3, keepdim=True)[1]
            target_max_qvals = th.gather(target_mac_out, 3, cur_max_actions).squeeze(3)
        else:
            target_max_qvals = target_mac_out.max(dim=3)[0]

        # Mix
        if self.mixer is not None:
            chosen_action_qvals = self.mixer(chosen_action_qvals, batch["state"][:, :-1])
            target_max_qvals = self.target_mixer(target_max_qvals, batch["state"][:, 1:])
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -