752f17f65ff851521b00f699e32f45e14945f069,tests/algorithms/test_td.py,,test_sarsa_lambda_continuous,#,141

Before Change

                      mdp_continuous.info.observation_space.high[0], 10)
    s_2 = np.linspace(mdp_continuous.info.observation_space.low[1],
                      mdp_continuous.info.observation_space.high[1], 10)
    for i in s_1:
        for j in s_2:
            alg._update(np.array([i, j]), np.array([1]), 100, np.array([0, 0]),
                        0)

    test_w = np.array([[0, 0, 0, 0],
                       [320.43, 399.8616, 340.397, 417.218],
                       [0, 0, 0, 0]])

After Change

    core = Core(agent, mdp_continuous)

    // Train
    core.learn(n_steps=100, n_steps_per_fit=1, quiet=True)

    test_w = np.array([-16.38428419, 0., -14.31250136, 0., -15.68571525, 0.,
                       -10.15663821, 0., -15.0545445, 0., -8.3683605, 0.])

Instances