agents/bc_cvae.py [88:102]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    def train(self, replay_buffer, iterations, batch_size=100):

        for it in range(iterations):
            # Sample replay buffer / batch
            state, action, next_state, reward, not_done = replay_buffer.sample(batch_size)

            # Variational Auto-Encoder Training
            recon, mean, std = self.vae(state, action)
            recon_loss = F.mse_loss(recon, action)
            KL_loss = -0.5 * (1 + torch.log(std.pow(2)) - mean.pow(2) - std.pow(2)).mean()
            vae_loss = recon_loss + 0.5 * KL_loss

            self.vae_optimizer.zero_grad()
            vae_loss.backward()
            self.vae_optimizer.step()
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



agents/bc_mmd.py [184:198]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    def train(self, replay_buffer, iterations, batch_size=100):

        for it in range(iterations):
            # Sample replay buffer / batch
            state, action, next_state, reward, not_done = replay_buffer.sample(batch_size)

            # Variational Auto-Encoder Training
            recon, mean, std = self.vae(state, action)
            recon_loss = F.mse_loss(recon, action)
            KL_loss = -0.5 * (1 + torch.log(std.pow(2)) - mean.pow(2) - std.pow(2)).mean()
            vae_loss = recon_loss + 0.5 * KL_loss

            self.vae_optimizer.zero_grad()
            vae_loss.backward()
            self.vae_optimizer.step()
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -