nn_bandit.py 文件源码

def choose_arm(x, experts, explore):
    n_arms = len(experts)
    # make predictions
    preds = [expert.predict(x) for expert in experts]
    # get best arm
    arm_max = np.nanargmax(preds)
    # create arm selection probabilities
    P = [(1-explore)*(arm==arm_max) + explore/n_arms for arm in range(n_arms)]
    # select an arm
    chosen_arm = np.random.choice(np.arange(n_arms), p=P)
    pred = preds[chosen_arm]
    return chosen_arm, pred