test_pgt.py 文件源码

def make_model(self, env):
        n_dim_obs = env.observation_space.low.size
        n_dim_action = env.action_space.low.size
        n_hidden_channels = 50

        policy = policies.FCGaussianPolicy(
            n_input_channels=n_dim_obs,
            n_hidden_layers=2,
            n_hidden_channels=n_hidden_channels,
            action_size=n_dim_action,
            min_action=env.action_space.low,
            max_action=env.action_space.high)

        q_func = q_function.FCSAQFunction(
            n_dim_obs=n_dim_obs,
            n_dim_action=n_dim_action,
            n_hidden_layers=2,
            n_hidden_channels=n_hidden_channels)

        return chainer.Chain(policy=policy, q_function=q_func)