values in those ranges for each trial. Let's discuss this strategy next! Random Search Random Search (RS) samples trials randomly from the search space. For discrete parameters, it picks a value from the specified range. For example, given two hyperparameters and such that is real valued in range and , RS can generate an arbitrary number of trials. For 5 trials, one possible trial set can be and for 7

R = 0 Rs = [] 预览版202112 第 14 章 强化学习 20 for r in reward[::-1]: R = r + gamma * R Rs.insert(0, R) Rs = tf.constant(Rs, dtype=tf.float32) as tape2: # 取出 R(st)，[b,1] v_target = tf.expand_dims(tf.gather(Rs, index, axis=0), axis =1) # 计算 v(s)预测值，也就是偏置 b，我们后面会介绍为什么写成 v