用强化学习DQN算法，训练AI模型来玩合成大西瓜游戏，提供Keras版本和PARL（paddle）版本

Last update: Dec 17, 2022

Overview

用强化学习玩合成大西瓜

代码地址：https://github.com/Sharpiless/play-daxigua-using-Reinforcement-Learning

用强化学习DQN算法，训练AI模型来玩合成大西瓜游戏，提供Keras版本、PARL（paddle）版本和pytorch版本。

B站：https://space.bilibili.com/470550823

CSDN：https://blog.csdn.net/weixin_44936889

AI Studio：https://aistudio.baidu.com/aistudio/personalcenter/thirdview/67156

Github：https://github.com/Sharpiless

1. 打开游戏：

这里使用pygame重写了大西瓜游戏，并封装为适合RL环境的代码。

解压图片素材：

unzip res.zip

运行：

python Main.py

即可开始游戏：

2. 训练RL模型：

RL算法采用DQN算法，其中Keras版本使用了简单的卷积神经网络来计算Q值，PRAL版本使用ResNet。

运行：

python train_keras.py

或者

python train_paddle.py

或者

python train_torch.py

开始训练：

关注我的公众号：

感兴趣的同学关注我的公众号——可达鸭的深度学习教程：

PaddleRobotics is an open-source algorithm library for robots based on Paddle, including open-source parts such as human-robot interaction, complex motion control, environment perception, SLAM positioning, and navigation.

简体中文 | English PaddleRobotics paddleRobotics是基于paddle的机器人开源算法库集，包括人机交互、复杂运动控制、环境感知、slam定位导航等开源算法部分。人机交互主动多模交互技术TFVT-HRI 主动多模交互技术是通过视觉、语音、触摸传感器等输入机器人

185 Dec 26, 2022

Paddle-RLBooks is a reinforcement learning code study guide based on pure PaddlePaddle.

Paddle-RLBooks Welcome to Paddle-RLBooks which is a reinforcement learning code study guide based on pure PaddlePaddle. 欢迎来到Paddle-RLBooks，该仓库主要是针对强化学

117 Dec 12, 2022

Paddle-Adversarial-Toolbox (PAT) is a Python library for Deep Learning Security based on PaddlePaddle.

Paddle-Adversarial-Toolbox Paddle-Adversarial-Toolbox (PAT) is a Python library for Deep Learning Security based on PaddlePaddle. Model Zoo Common FGS

17 Nov 8, 2022

Paddle implementation for "Highly Efficient Knowledge Graph Embedding Learning with Closed-Form Orthogonal Procrustes Analysis" (NAACL 2021)

ProcrustEs-KGE Paddle implementation for Highly Efficient Knowledge Graph Embedding Learning with Orthogonal Procrustes Analysis 🙈 A more detailed re

4 Jun 9, 2021

Paddle implementation for "Cross-Lingual Word Embedding Refinement by ℓ1 Norm Optimisation" (NAACL 2021)

L1-Refinement Paddle implementation for "Cross-Lingual Word Embedding Refinement by ℓ1 Norm Optimisation" (NAACL 2021) 🙈 A more detailed readme is co

4 Jun 9, 2021

x-transformers-paddle 2.x version

x-transformers-paddle x-transformers-paddle 2.x version paddle 2.x版本 https://github.com/lucidrains/x-transformers 。 requirements paddlepaddle-gpu==2.2

7 Dec 8, 2022

This is the paddle code for SeBoW(Self-Born wiring for neural trees), a kind of neural tree born form a large search space

SeBoW: Self-Born Wiring for neural trees(PaddlePaddle version) This is the paddle code for SeBoW(Self-Born wiring for neural trees), a kind of neural

13 Dec 8, 2022

Comments

多个水果同时碰撞的问题

产生问题的情况

$B_1$, $B_2$, $B_3$是同类型的水果，$B_2$同时与$B_1$,$B_3$碰撞，会同时合并产生2个更高一级的水果，这两个水果又会合并产生高两级的水果。

问题

判断碰撞时，是一对一对检测的。第一对($B_1$,$B_2$)处理后，会删除$B_1$,$B_2$，再处理第二对时，没有检测$B_1$,$B_2$是否还存在，而直接生成了第二个更高一级的水果。

解决

增加检测当前碰撞对的水果是否都存在的判断，若任何一个不存在了，则不做任何操作。

opened by mangoleaves 0

用强化学习DQN算法，训练AI模型来玩合成大西瓜游戏，提供Keras版本和PARL（paddle）版本

Related tags

Overview

用强化学习玩合成大西瓜

1. 打开游戏：

2. 训练RL模型：

关注我的公众号：

You might also like...

PaddleRobotics is an open-source algorithm library for robots based on Paddle, including open-source parts such as human-robot interaction, complex motion control, environment perception, SLAM positioning, and navigation.

Paddle-RLBooks is a reinforcement learning code study guide based on pure PaddlePaddle.

Paddle-Adversarial-Toolbox (PAT) is a Python library for Deep Learning Security based on PaddlePaddle.

Paddle implementation for "Highly Efficient Knowledge Graph Embedding Learning with Closed-Form Orthogonal Procrustes Analysis" (NAACL 2021)

Paddle implementation for "Cross-Lingual Word Embedding Refinement by ℓ1 Norm Optimisation" (NAACL 2021)

x-transformers-paddle 2.x version

This is the paddle code for SeBoW(Self-Born wiring for neural trees), a kind of neural tree born form a large search space

SplineConv implementation for Paddle.

Sparse-dense operators implementation for Paddle

YOLOX-Paddle - A reproduction of YOLOX by PaddlePaddle

Paddle pit - Rethinking Spatial Dimensions of Vision Transformers

Paddle-Skeleton-Based-Action-Recognition - DecoupleGCN-DropGraph, ASGCN, AGCN, STGCN

Comments

多个水果同时碰撞的问题

产生问题的情况

问题

解决

Owner

Paddle-Adversarial-Toolbox (PAT) is a Python library for Deep Learning Security based on PaddlePaddle.

Paddle implementation for "Highly Efficient Knowledge Graph Embedding Learning with Closed-Form Orthogonal Procrustes Analysis" (NAACL 2021)

Paddle implementation for "Cross-Lingual Word Embedding Refinement by ℓ1 Norm Optimisation" (NAACL 2021)

x-transformers-paddle 2.x version

This is the paddle code for SeBoW(Self-Born wiring for neural trees), a kind of neural tree born form a large search space

SplineConv implementation for Paddle.

Sparse-dense operators implementation for Paddle

YOLOX-Paddle - A reproduction of YOLOX by PaddlePaddle

Paddle pit - Rethinking Spatial Dimensions of Vision Transformers

Paddle-Skeleton-Based-Action-Recognition - DecoupleGCN-DropGraph, ASGCN, AGCN, STGCN