rlkit/torch/sac/bear.py [51:109]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    ):
        super().__init__()
        self.env = env
        self.policy = policy
        self.qf1 = qf1
        self.qf2 = qf2
        self.target_qf1 = target_qf1
        self.target_qf2 = target_qf2
        self.vae = vae
        self.soft_target_tau = soft_target_tau
        self.target_update_period = target_update_period

        self.plotter = plotter
        self.render_eval_paths = render_eval_paths

        self.qf_criterion = nn.MSELoss()
        self.vf_criterion = nn.MSELoss()

        self.policy_optimizer = optimizer_class(
            self.policy.parameters(),
            lr=policy_lr,
        )
        self.qf1_optimizer = optimizer_class(
            self.qf1.parameters(),
            lr=qf_lr,
        )
        self.qf2_optimizer = optimizer_class(
            self.qf2.parameters(),
            lr=qf_lr,
        )
        self.vae_optimizer = optimizer_class(
            self.vae.parameters(),
            lr=3e-4,
        )

        self.mode = mode
        if self.mode == 'auto':
            self.log_alpha = ptu.zeros(1, requires_grad=True)
            self.alpha_optimizer = optimizer_class(
                [self.log_alpha],
                lr=1e-3,
            )
        self.mmd_sigma = mmd_sigma
        self.kernel_choice = kernel_choice
        self.num_samples_mmd_match = num_samples_mmd_match
        self.policy_update_style = policy_update_style
        self.target_mmd_thresh = target_mmd_thresh

        self.discount = discount
        self.reward_scale = reward_scale
        self.eval_statistics = OrderedDict()
        self._n_train_steps_total = 0
        self._need_to_update_eval_statistics = True

        self.discrete = False
        self._current_epoch = 0
        self._policy_update_ctr = 0
        self._num_q_update_steps = 0
        self._num_policy_update_steps = 0
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



rlkit/torch/sac/uwac_dropout.py [58:116]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    ):
        super().__init__()
        self.env = env
        self.policy = policy
        self.qf1 = qf1
        self.qf2 = qf2
        self.target_qf1 = target_qf1
        self.target_qf2 = target_qf2
        self.vae = vae
        self.soft_target_tau = soft_target_tau
        self.target_update_period = target_update_period

        self.plotter = plotter
        self.render_eval_paths = render_eval_paths

        self.qf_criterion = nn.MSELoss()
        self.vf_criterion = nn.MSELoss()

        self.policy_optimizer = optimizer_class(
            self.policy.parameters(),
            lr=policy_lr,
        )
        self.qf1_optimizer = optimizer_class(
            self.qf1.parameters(),
            lr=qf_lr,
        )
        self.qf2_optimizer = optimizer_class(
            self.qf2.parameters(),
            lr=qf_lr,
        )
        self.vae_optimizer = optimizer_class(
            self.vae.parameters(),
            lr=3e-4,
        )

        self.mode = mode
        if self.mode == 'auto':
            self.log_alpha = ptu.zeros(1, requires_grad=True)
            self.alpha_optimizer = optimizer_class(
                [self.log_alpha],
                lr=1e-3,
            )
        self.mmd_sigma = mmd_sigma
        self.kernel_choice = kernel_choice
        self.num_samples_mmd_match = num_samples_mmd_match
        self.policy_update_style = policy_update_style
        self.target_mmd_thresh = target_mmd_thresh

        self.discount = discount
        self.reward_scale = reward_scale
        self.eval_statistics = OrderedDict()
        self._n_train_steps_total = 0
        self._need_to_update_eval_statistics = True

        self.discrete = False
        self._current_epoch = 0
        self._policy_update_ctr = 0
        self._num_q_update_steps = 0
        self._num_policy_update_steps = 0
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -