尼古拉斯·雷诺特(Nicholas Renotte)关于玩超级马里奥的强化学习模型的教程,
Tutorial from Nicholas Renotte on Reinforcement Learning model playing Super Mario, (2023-10-23, Jupyter Notebook, 0KB, 下载0次)
使用监督和无监督机器学习模型的组合来预测FIFA19中的玩家系数和值,
Using a combination of Supervised and Unsupervised Machine Learning models to predict player coefficients and value in FIFA19, (2019-01-25, Jupyter Notebook, 0KB, 下载0次)
PPO算法的张量流实现,以便使用Gymnasium环境玩Atari游戏,扩展为探索B...,
Tensorflow implementation of the PPO algorithm in order to play Atari games using Gymnasium Environments, extended with the Exploration Bonus by Random Network Distillation (2023-07-27, Jupyter Notebook, 0KB, 下载0次)
玩由你的手势控制的点心游戏。我使用了的mediapipe和opencvpython库来完成这一点。,
Play snack game which is controlled by your gesture. i have used mediapipe and opencv-python library for to do that., (2021-06-29, Jupyter Notebook, 0KB, 下载0次)
用手玩谷歌恐龙游戏。。。无需触摸键盘!,
Play the Google Dino Game with your hands... without touching the keyboard!, (2022-05-18, Jupyter Notebook, 0KB, 下载0次)
[WIP]通过观看YouTube玩艰苦探索游戏(Aytar等人,2018),
[WIP] Playing Hard Exploration Games by Watching YouTube (Aytar et al., 2018), (2019-01-31, Jupyter Notebook, 0KB, 下载0次)
在这个存储库中,我们利用少试学习与转移学习方法相结合的能力来处理对象开发任务...,
In this repository, we leverage the power of few-shot learning combined with a transfer learning approach to tackle the task of object detection. (2023-06-17, Jupyter Notebook, 0KB, 下载0次)
应用人工智能入门课程的内容-从基础知识到Web应用程序-边学习边构建和玩
Content for Applied AI introductory course - from basics to webapps - build and play while learning (2022-04-12, Jupyter Notebook, 74797KB, 下载0次)
自玩多智能体强化学习研究论文的可视化。streamlit带来的可视化效果
Visualizations for a research paper on Self-play multiagent reinforcement learning. Visualizations thanks to streamlit (2022-06-21, Jupyter Notebook, 8519KB, 下载0次)
由进化算法优化的神经网络代理,用于玩21点或21点(仅使用python numpy熊猫)
A Neural network Agent optimized by Evolutionary algorithms to play BlackJack or 21 (using only python numpy pandas) (2019-07-14, Jupyter Notebook, 39KB, 下载0次)
机器学习模型,预测人工智能玩家在TicTacToe游戏中的下一个最佳动作。
Machine learning model that predicts next best move for an AI player in a TicTacToe game. (2022-02-06, Jupyter Notebook, 3860KB, 下载0次)
一个笔记本与俄罗斯联邦储蓄银行AI的ru-DALE模型玩,使用英语提示。
A notebook to play with Sberbank AI s ru-DALLE model using English prompts. (2021-11-03, Jupyter Notebook, 1572KB, 下载0次)
BOMBERMAN-强化学习-Q-学习,使用Q学习来教人工智能代理玩一个简单的轰炸机人克隆。
BOMBERMAN-Reinforcement-Learning-Q-Learning,Using Q-learning to teach an AI agent play a simple BomberMan clone. (2019-10-07, Jupyter Notebook, 612KB, 下载0次)
deep_Q_learning_from_scratch,深度Q强化学习仅从视觉输入开始玩游戏。
deep_Q_learning_from_scratch,Deep Q Reinforcement learning to play games just from visual input. (2020-09-14, Jupyter Notebook, 1137KB, 下载0次)
RL超级马里奥兄弟,强化学习算法,用于学习玩超级马里奥兄弟。
RL-SuperMarioBros,Reinforcement learning algorithms implemented to learn to play Super Mario Bros. (2020-10-24, Jupyter Notebook, 73477KB, 下载0次)
深度学习教程,Talk很便宜,给我看看代码!深度学习,深度学习,玩得开心!
DeepLearningTutorial,Talk is cheap,show me the code ! Deep Learning,Leaning deep,Have fun! (2023-03-25, Jupyter Notebook, 6020KB, 下载0次)
2048-api,用于开发ML(模拟学习或强化学习)代理以玩游戏的教育api 2048
2048-api,Educational API for developing ML (imitation learning or reinforcement learning) agents to play game 2048 (2021-10-29, Jupyter Notebook, 677KB, 下载0次)
战列舰,使用强化学习(PPO)和openAI健身房训练玩战列舰的特工,
Agent trained to play battleship using reinforcement learning (PPO) and openAI
gym
, (2021-11-24, Jupyter Notebook, 35615KB, 下载0次)
在OpenAI Gym中玩Frozen-Lake-v0问题时的值迭代策略迭代、值迭代和策略迭代,
Value Iteration and Policy Iteration in playing Frozen-Lake-v0 problem in
OpenAI Gym.
, (2020-08-26, Jupyter Notebook, 10KB, 下载0次)
DQN雅达利突破,一个深度Q网络,训练在OpenAI健身房环境中玩雅达利突破游戏,
A Deep Q-Network trained to play Breakout Atari game on OpenAI Gym
environment.
, (2021-12-05, Jupyter Notebook, 12108KB, 下载0次)