eval_pol.py 文件源码

def predict(st,norm,bounds):

    rew = np.log(1+ (st[:,-1:]))

    a_x = bounds[0]
    b_x = bounds[2]

    eps = 1e-5

    rew = np.clip(rew,a_x+eps,b_x-eps)

    rew = logit((rew - a_x) / (b_x - a_x))

    st [:,-1:] = rew  

    State  = np.zeros((1,61))
    State[0,:] = np.hstack((st[0,0],st[:,[1,2,3,-1]].ravel()))

    X = (State  - norm[0]) / norm[1]
    return np.round(policy_network(X)[0,:],4)