def test_boltzmann_q(self):
x = np.asarray([1 / 2, 1 / 2])
payoff = np.asarray([[1, 0], [0, 1]], dtype=np.float32)
temperature = 1
np.testing.assert_array_equal(
dynamics.boltzmannq(x, payoff, temperature),
_q_learning_dynamics(x, payoff, temperature))
def boltzmann_qlearning(state, fitness, temperature=0.01):
return egt_dyn.boltzmannq(state, fitness, temperature)