模拟不同轮盘赌策略的两个脚本。用来证明随着时间的推移玩轮盘赌不可避免的损失。
A couple scripts that simulate different roulette strategies. Used to prove the inevitable losses of playing roulette over time. (2024-04-08, Jupyter Notebook, 0KB, 下载0次)
为俄罗斯方块游戏制作UI，然后创建可以自己玩俄罗斯方块的AI（RL代理）
Make the UI for a tetris game and then create an AI (RL agent) that can play tetris on its own (2024-01-05, Jupyter Notebook, 0KB, 下载0次)
开发了一个强化学习模型，使用Python、RL库、PPO算法和模型玩马里奥游戏。项目利用...，
Developed a Reinforcement Learning model to play the Mario game using Python, RL libraries, PPO Algorithm, and model. The project utilises techniques like Grayscaling, Vectorization, Frame Stacking, Client Conversation, and the Reinforcement Learning Model training. (2023-10-18, Jupyter Notebook, 0KB, 下载0次)
在这个可乐笔记本中，我使用Tensorflow来玩和实验人工智能艺术，特别是深度梦算法。，
In this colab notebook, I use Tensorflow to play and experiment with AI Art, in specific with the Deep Dream Algorithm., (2022-10-18, Jupyter Notebook, 0KB, 下载0次)
通过本技术简介探索人工智能的基础。学习解决问题、玩游戏、知识表示等功能...，
Explore the foundations of AI with this technical intro. Learn problem-solving, game playing, knowledge representation, & more to facilitate intelligent computer behavior. Apply techniques to real systems, including LISP programming. Gain insight into machine learning, & perception interpretation (2023-09-15, Jupyter Notebook, 0KB, 下载0次)
训练用于玩益智游戏俄罗斯方块的算法。该实现使用了稳定的基线3和openai健身房。，
An algorithm trained to play a the puzzle game Tetris. This implementation makes use of stable baselines 3 and openai gymnasium., (2023-09-10, Jupyter Notebook, 0KB, 下载0次)
这是一个存储库，用于分析和实现使用人工智能（特别是增强学习）在图上玩随机游戏的代理...，
This is a repository for analysing and implementing agents that play stochastic games on graphs using AI and especially reinforcement learning (2023-08-23, 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)
训练代理玩赛车游戏TrackMania，在PyTorch和tmrl环境中从头开始使用PPO（近似策略优化）...，
training an agent to play the racecar game TrackMania, using PPO (Proximal Policy Optimization) from scratch in PyTorch and the tmrl environment (2023-07-22, Jupyter Notebook, 0KB, 下载0次)
通过模拟进化创建游戏玩家代理-Otago Uni的COSC343论文的遗传人工智能分配，
Creating game playing agents via simulated evolution - Genetic AI assignment for Otago Uni s COSC343 paper, (2021-10-31, Jupyter Notebook, 0KB, 下载0次)
第一届学校人工智能大赛的初学者文件。目标是创建一个能够玩Connect4的代理，
Starter files for the First School of AI Competition. The objective is to create an agent capable of playing Connect4, (2019-05-15, Jupyter Notebook, 0KB, 下载0次)
创建了一个AI增强模型来玩cartpoe。用两种不同的算法对模型进行了100.000步的训练...
Created an AI reinfocement-model to play cartpoe. The model is trained with 100.000 steps with two different algoritm types PPO and DQN (2021-09-22, Jupyter Notebook, 6KB, 下载0次)
用于训练人工智能模型以使用PyTorch和EfficientNet玩铬恐龙游戏的存储库
Repository for training an AI model to play the Chrome Dino Game using PyTorch and EfficientNet (2023-06-09, Jupyter Notebook, 13KB, 下载0次)
使用卷积自动编码器和进化算法玩ATARI游戏。团队名称：bad_skiers_evolved（D...
Playing ATARI games using a convolutional autoencoder and an evolutionary algorithm. Team name: bad_skiers_evolved (DeepHack.RL) (2017-02-12, Jupyter Notebook, 509KB, 下载0次)
使用定向梯度直方图（HOG）从斯坦福数据集中提取特征，并使用支持向量机...
Extract features from the Stanford Dataset using Histogram of Oriented Gradients (HOG) and use Supported Vector Machine (SVM) to map the features to the assigned labels. Next, use Non-Maximum Suppression and Heatmap method to find the best bounding box on the face. (2023-06-01, Jupyter Notebook, 4955KB, 下载0次)
网络摄像头游戏控制器，基于人工智能设计，通过网络摄像头捕捉玩家双手的运动来控制游戏。
webcam-game-controller,Design based on artificial intelligence to control games through the movement of the players hands captured by webcam. (2021-05-14, Jupyter Notebook, 9022KB, 下载0次)
超级马里奥兄弟强化学习，我使用Stable-Baselines3玩NES超级马里奥兄弟的强化学习模型的实现。
super-mario-bros-reinforcement-learning,My implementation of a reinforcement learning model using Stable-Baselines3 to play the NES Super Mario Bros. (2023-04-21, Jupyter Notebook, 51757KB, 下载0次)
跳棋MCTS，一个训练神经网络通过与蒙特卡洛树搜索相结合的自我游戏来玩跳棋的项目。
Checkers-MCTS,A project to train a neural network to play Checkers through self-play combined with Monte Carlo Tree Search. (2021-07-27, Jupyter Notebook, 144271KB, 下载0次)
stanford-cs231n-assignments-2020，这个存储库包含我对斯坦福大学cs231n“视觉卷积神经网络”作业的解决方案...
This repository contains my solutions to the assignments for Stanford s CS231n "Convolutional Neural Networks for Visual Recognition" (Spring 2020). (2021-07-11, Jupyter Notebook, 210835KB, 下载0次)
GraphNeuralNetWork,玩转图神经网络和知识图谱的相关算法:GCN,GAT,GAFM,GAAFM,GraphSage,W2V,TRANSe
GraphNeural Network, related algorithms for playing graph neural networks and knowledge graphs: GCN, GAT, GAFM, GAAFM, GraphSage, W2V, TRANSe (2023-04-12, Jupyter Notebook, 22146KB, 下载0次)