这是Softuni数据科学期末考试的期末项目。它可以用于与dashcam软件集成，以检测…
This is the final project for the Softuni Data Science Final Exam. It can be used for integrating with dashcam software for detection of … (2024-01-21, Jupyter Notebook, 0KB, 下载0次)
使用强化学习开发可以玩经典蛇游戏的代理
Using Reinforcement Learning to develop an agent that can play the classic snake game (2024-01-18, Jupyter Notebook, 0KB, 下载0次)
使用近端策略优化训练人工智能，以在自定义pong环境中玩，
AI trained using proximal policy optimization to play on a custom pong environment, (2023-10-27, Jupyter Notebook, 0KB, 下载0次)
一个AI程序，学习玩2003 GBA游戏Fire Emblem，
An AI program that learns to play the 2003 GBA game Fire Emblem, (2019-05-07, Jupyter Notebook, 0KB, 下载0次)
实施DeepMind的Deep Q-Networks以玩Atari游戏-强化学习项目，
Implementing DeepMind s Deep Q-Networks for playing Atari games - A project in reinforcement learning, (2023-08-08, Jupyter Notebook, 0KB, 下载0次)
在本报告中，您可以找到我2017年斯坦福大学CS231n视觉识别课程作业的解决方案...
In this repo you can find my solutions for 2017 assignments of the CS231n course taught by Stanford on visual recognition. Spring 2017 solutions are for both deep learning frameworks: TensorFlow and PyTorch. (2018-05-10, Jupyter Notebook, 26314KB, 下载0次)
实施和训练A2C和NEAT代理玩松鸡游戏。
Implementing and training A2C and NEAT agents to play flappy bird game. (2021-07-18, Jupyter Notebook, 9016KB, 下载0次)
训练PPO代理使用稳定基线3、Optuna和PyTorch玩街霸2
Trained a PPO agent to play Street Fighter 2 using Stable Baselines 3, Optuna, and PyTorch (2023-01-09, Jupyter Notebook, 310872KB, 下载0次)
在信用卡欺诈数据集上玩scikit learn和Deepnote笔记本
playing with scikit-learn and Deepnote notebooks on a credit card fraud dataset (2020-05-21, Jupyter Notebook, 10286KB, 下载0次)
使用遗传编程和深度学习玩Minecraft的最终人工智能硕士项目
Final AI MSc Project using Genetic Programming and Deep Learning to play Minecraft (2022-12-08, Jupyter Notebook, 23724KB, 下载0次)
深度强化学习模型玩骰子游戏knifel。
Deep reinforcement learning model to play the dice game kniffel. (2023-04-28, Jupyter Notebook, 51473KB, 下载0次)
通过强化学习训练的AI战舰玩家
An AI Battleship Player trained with Reinforcement learning (2022-12-08, Jupyter Notebook, 48KB, 下载0次)
AI-Index-2020，该存储库为斯坦福大学人工智能指数项目提供了对数据和脚本的透明访问...
This repository provides transparent access to data and scripts for the AI Index project, at the Stanford Institute for Human-Centered Artificial Intelligence (HAI). (2020-08-03, Jupyter Notebook, 78175KB, 下载0次)
FPL_LP_GA，用线性规划和遗传算法玩梦幻英超
FPL_LP_GA,Playing Fantasy Premier League with Linear Programming and Genetic Algorithms (2021-10-31, Jupyter Notebook, 13KB, 下载0次)
解决方案-Stanford-cs131计算机视觉基础与应用，秋季完整解决方案斯坦福课程cs131的1617次迭代：计算机视觉基础和应用
Solutions-Stanford-cs131-Computer-Vision-Foundations-and-Application,Full solutions for fall1617 iteration of Stanford course CS131: Computer Vision Foundations and Applications (2018-08-15, Jupyter Notebook, 53178KB, 下载0次)
Hangman，演示如何使用CNTK训练神经网络玩Hangman的教程
Hangman,A tutorial demonstrating how to train a neural network to play hangman using CNTK (2017-11-02, Jupyter Notebook, 324KB, 下载1次)
play_with_deep_reinforcement_learning,玩转深度强化学习
play_ with_ deep_ reinforcement_ Learning, playing deep reinforcement learning (2021-08-21, Jupyter Notebook, 94KB, 下载0次)
CS231n,斯坦福李飞飞深度学习课程的课后作业,有3个部分Assignment #1: Image Classification, kNN, SVM, Softmax, Neural NetworkAssignment #2: Fully-Con...
CS231n, the homework for Stanford Li Feifei s deep learning course, has three parts Assignment # 1: Image Classification, kNN, SVM, Softmax, Neural NetworkAssignment # 2: Full Con (2017-12-05, Jupyter Notebook, 8646KB, 下载0次)
使用RL的月球着陆器，模型学习使用DQN和遗传算法玩月球着陆器<https:gym.openai.com envs LunarLander-v2>，
使用RL的月球着陆器，模型学习使用DQN和遗传算法玩月球着陆器<https:gym.openai.com envs LunarLander-v2>， (2018-07-14, Jupyter Notebook, 2007KB, 下载0次)
Muzero，重新实现Muzero算法，AlphaZero的继任者，玩openai健身房游戏，
Re-implementation of MuZero algorithm, successor of AlphaZero, to play openai
gym games.
, (2020-03-16, Jupyter Notebook, 14KB, 下载0次)