From 19122bd5890e554a21920aad97331b605700e958 Mon Sep 17 00:00:00 2001 From: Yibing Liu Date: Thu, 29 Aug 2019 11:27:24 +0800 Subject: [PATCH] Update README.md (#3217) --- README.md | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index 1910c414..2769bcc3 100644 --- a/README.md +++ b/README.md @@ -346,9 +346,9 @@ PaddlePaddle 提供了丰富的计算单元，使得用户可以采用模块化 | 模型名称 | 模型简介 | | ------------------------------------------------------------ | ------------------------------------------------------------ | | [DeepASR](https://github.com/PaddlePaddle/models/blob/develop/PaddleSpeech/DeepASR/README_cn.md) | 利用Fluid框架完成语音识别中声学模型的配置和训练，并集成 Kaldi 的解码器 | -| [DQN](https://github.com/PaddlePaddle/models/blob/develop/PaddleRL/DeepQNetwork/README_cn.md) | value based强化学习算法，第一个成功地将深度学习和强化学习结合起来的模型 | -| [DoubleDQN](https://github.com/PaddlePaddle/models/blob/develop/PaddleRL/DeepQNetwork/README_cn.md) | 将Double Q的想法应用在DQN上，解决过优化问题 | -| [DuelingDQN](https://github.com/PaddlePaddle/models/blob/develop/PaddleRL/DeepQNetwork/README_cn.md) | 改进了DQN模型，提高了模型的性能 | +| [DQN](https://github.com/PaddlePaddle/models/blob/develop/legacy/PaddleRL/DeepQNetwork/README_cn.md) | value based强化学习算法，第一个成功地将深度学习和强化学习结合起来的模型 | +| [DoubleDQN](https://github.com/PaddlePaddle/models/blob/develop/legacy/PaddleRL/DeepQNetwork/README_cn.md) | 将Double Q的想法应用在DQN上，解决过优化问题 | +| [DuelingDQN](https://github.com/PaddlePaddle/models/blob/develop/legacy/PaddleRL/DeepQNetwork/README_cn.md) | 改进了DQN模型，提高了模型的性能 | ## License This tutorial is contributed by [PaddlePaddle](https://github.com/PaddlePaddle/Paddle) and licensed under the [Apache-2.0 license](LICENSE). -- GitLab