752f17f65ff851521b00f699e32f45e14945f069,tests/algorithms/test_td.py,,test_true_online_sarsa_lambda,#,194

Before Change

    s_1 = np.linspace(mdp_continuous.info.observation_space.low[0],
                      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:

After Change

    core = Core(agent, mdp_continuous)

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

    test_w = np.array([-17.27410736, 0., -15.04386343, 0., -16.6551805, 0.,
                       -11.31383707, 0., -16.11782002, 0., -9.6927357, 0.])

Instances