agent/baseline_agent.py [190:258]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    @property
    def alpha(self):
        return self.log_alpha.exp()

    def select_action(self, obs):
        with torch.no_grad():
            obs = torch.FloatTensor(obs).to(self.device)
            obs = obs.unsqueeze(0)
            mu, _, _, _ = self.actor(
                obs, compute_pi=False, compute_log_pi=False
            )
            return mu.cpu().data.numpy().flatten()

    def sample_action(self, obs):
        with torch.no_grad():
            obs = torch.FloatTensor(obs).to(self.device)
            obs = obs.unsqueeze(0)
            mu, pi, _, _ = self.actor(obs, compute_log_pi=False)
            return pi.cpu().data.numpy().flatten()

    def update_critic(self, obs, action, reward, next_obs, not_done, L, step):
        with torch.no_grad():
            _, policy_action, log_pi, _ = self.actor(next_obs)
            target_Q1, target_Q2 = self.critic_target(next_obs, policy_action)
            target_V = torch.min(target_Q1,
                                 target_Q2) - self.alpha.detach() * log_pi
            target_Q = reward + (not_done * self.discount * target_V)

        # get current Q estimates
        current_Q1, current_Q2 = self.critic(obs, action, detach_encoder=False)
        critic_loss = F.mse_loss(current_Q1,
                                 target_Q) + F.mse_loss(current_Q2, target_Q)
        L.log('train_critic/loss', critic_loss, step)

        # Optimize the critic
        self.critic_optimizer.zero_grad()
        critic_loss.backward()
        self.critic_optimizer.step()

        self.critic.log(L, step)

    def update_actor_and_alpha(self, obs, L, step):
        # detach encoder, so we don't update it with the actor loss
        _, pi, log_pi, log_std = self.actor(obs, detach_encoder=True)
        actor_Q1, actor_Q2 = self.critic(obs, pi, detach_encoder=True)

        actor_Q = torch.min(actor_Q1, actor_Q2)
        actor_loss = (self.alpha.detach() * log_pi - actor_Q).mean()

        L.log('train_actor/loss', actor_loss, step)
        L.log('train_actor/target_entropy', self.target_entropy, step)
        entropy = 0.5 * log_std.shape[1] * (1.0 + np.log(2 * np.pi)
                                            ) + log_std.sum(dim=-1)
        L.log('train_actor/entropy', entropy.mean(), step)

        # optimize the actor
        self.actor_optimizer.zero_grad()
        actor_loss.backward()
        self.actor_optimizer.step()

        self.actor.log(L, step)

        self.log_alpha_optimizer.zero_grad()
        alpha_loss = (self.alpha *
                      (-log_pi - self.target_entropy).detach()).mean()
        L.log('train_alpha/loss', alpha_loss, step)
        L.log('train_alpha/value', self.alpha, step)
        alpha_loss.backward()
        self.log_alpha_optimizer.step()
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



agent/bisim_agent.py [133:201]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    @property
    def alpha(self):
        return self.log_alpha.exp()

    def select_action(self, obs):
        with torch.no_grad():
            obs = torch.FloatTensor(obs).to(self.device)
            obs = obs.unsqueeze(0)
            mu, _, _, _ = self.actor(
                obs, compute_pi=False, compute_log_pi=False
            )
            return mu.cpu().data.numpy().flatten()

    def sample_action(self, obs):
        with torch.no_grad():
            obs = torch.FloatTensor(obs).to(self.device)
            obs = obs.unsqueeze(0)
            mu, pi, _, _ = self.actor(obs, compute_log_pi=False)
            return pi.cpu().data.numpy().flatten()

    def update_critic(self, obs, action, reward, next_obs, not_done, L, step):
        with torch.no_grad():
            _, policy_action, log_pi, _ = self.actor(next_obs)
            target_Q1, target_Q2 = self.critic_target(next_obs, policy_action)
            target_V = torch.min(target_Q1,
                                 target_Q2) - self.alpha.detach() * log_pi
            target_Q = reward + (not_done * self.discount * target_V)

        # get current Q estimates
        current_Q1, current_Q2 = self.critic(obs, action, detach_encoder=False)
        critic_loss = F.mse_loss(current_Q1,
                                 target_Q) + F.mse_loss(current_Q2, target_Q)
        L.log('train_critic/loss', critic_loss, step)

        # Optimize the critic
        self.critic_optimizer.zero_grad()
        critic_loss.backward()
        self.critic_optimizer.step()

        self.critic.log(L, step)

    def update_actor_and_alpha(self, obs, L, step):
        # detach encoder, so we don't update it with the actor loss
        _, pi, log_pi, log_std = self.actor(obs, detach_encoder=True)
        actor_Q1, actor_Q2 = self.critic(obs, pi, detach_encoder=True)

        actor_Q = torch.min(actor_Q1, actor_Q2)
        actor_loss = (self.alpha.detach() * log_pi - actor_Q).mean()

        L.log('train_actor/loss', actor_loss, step)
        L.log('train_actor/target_entropy', self.target_entropy, step)
        entropy = 0.5 * log_std.shape[1] * (1.0 + np.log(2 * np.pi)
                                            ) + log_std.sum(dim=-1)
        L.log('train_actor/entropy', entropy.mean(), step)

        # optimize the actor
        self.actor_optimizer.zero_grad()
        actor_loss.backward()
        self.actor_optimizer.step()

        self.actor.log(L, step)

        self.log_alpha_optimizer.zero_grad()
        alpha_loss = (self.alpha *
                      (-log_pi - self.target_entropy).detach()).mean()
        L.log('train_alpha/loss', alpha_loss, step)
        L.log('train_alpha/value', self.alpha, step)
        alpha_loss.backward()
        self.log_alpha_optimizer.step()
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -