forked from PaddlePaddle/PARL
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathutils.py
28 lines (24 loc) · 1.15 KB
/
utils.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
# Copyright (c) 2018 PaddlePaddle Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import numpy as np
def calc_discount_norm_reward(reward_list, gamma):
discount_norm_reward = np.zeros_like(reward_list)
discount_cumulative_reward = 0
for i in reversed(range(0, len(reward_list))):
discount_cumulative_reward = (
gamma * discount_cumulative_reward + reward_list[i])
discount_norm_reward[i] = discount_cumulative_reward
discount_norm_reward = discount_norm_reward - np.mean(discount_norm_reward)
discount_norm_reward = discount_norm_reward / np.std(discount_norm_reward)
return discount_norm_reward