DDQN从像素开始训练,通过Farama Gymnasium玩Atari游戏。在Pong和Breakout上测试
DDQN trained from pixels to play Atari games through Farama Gymnasium. Tested on Pong and Breakout (2024-04-15, Jupyter Notebook, 0KB, 下载0次)
利用IPL的记分板,我们试图分析IPL_2022玩家的趋势和成就
Taking use of IPL s scoreboard we are trying to analyse the trends and achievements of the players in IPL_2022 (2024-03-01, Jupyter Notebook, 0KB, 下载0次)
使用强化学习的遗传算法选择MLP的权重来玩月球着陆器。
Genetic algorithm to select the weights of a MLP to play lunar lander using Reinforcement Learning. (2024-02-29, Jupyter Notebook, 0KB, 下载0次)
斯坦福STATS 202的最终项目:数据挖掘和分析。基于智能手机传感器数据的数据探索和ML模型构建。用R和Python进行
Final Project from Stanford STATS 202: Data Mining and Analysis. Data exploration and ML model building on smartphone sensor data. Conducted in R and Python (2024-02-16, Jupyter Notebook, 0KB, 下载0次)
一个使用决斗深度Q网络(DDQN)架构的单代理强化学习项目,在Open中玩Atari的“Pacman女士”…
A single-agent reinforcement learning project utilizing a Dueling Deep Q-Network (DDQN) architecture to play Atari s "Ms. Pacman" in Open… (2024-01-21, Jupyter Notebook, 0KB, 下载0次)
数据帧概述,通过熊猫和numpy玩行和列。访问和修改数据以进行数据分析
Data Frame overview and playing with rows & columns through pandas & numpy. Accessing and Modifying Data for Data analysis (2023-12-07, Jupyter Notebook, 0KB, 下载0次)
我是一名热爱dota2的玩家,这是我的第一个dota2数据分析项目
I am a player who loves dota2. This is my first dota2 data analysis project (2023-11-10, Jupyter Notebook, 0KB, 下载0次)
该存储库包含深度Q网络(DQN)算法及其变体DDQN的实现,用于训练代理玩LunarLa...
This repository contains an implementation of the Deep Q-Network (DQN) algorithm and its variant DDQN to train agents to play the LunarLander-v2 environment in OpenAI Gym. ???? (2023-11-04, Jupyter Notebook, 0KB, 下载0次)
该项目的重点是建立一个对象检测模型,检测来自两个地理位置的垃圾:福尔柯克,苏格兰和潘...
This Project focuses on building an Object detection model that detects Litter from two geographical locations: Falkirk, Scotland and Punalur, India (2023-11-04, Jupyter Notebook, 0KB, 下载0次)
一个具有定制环境的DQN模型,教计算机如何玩著名的游戏,Google Chrome的Dino,
A DQN model with custom-built environment to teach the computer how to play the famous game, Dino from Google Chrome, (2023-10-13, Jupyter Notebook, 0KB, 下载0次)
包含斯坦福大学和Deeplea...的机器学习专业编程任务的可选实验室和解决方案...,
Contains Optional Labs and Solutions of Programming Assignment for the Machine Learning Specialization By Stanford University and Deeplearning.ai - Coursera (2023) by Prof. Andrew NG (2023-09-24, Jupyter Notebook, 0KB, 下载0次)
从头开始实施著名的boardgame Splender,并训练DQN代理,以最大限度地减少每个玩家的回合数,
Implement from scratch the famous boardgame Splendor and train a DQN agent to minimize the number of turns done by each player, (2023-09-17, Jupyter Notebook, 0KB, 下载0次)
该项目是训练强化学习(RL)代理使用Double Deep...玩经典Atari Breakout游戏的演示...,
This project is a demonstration of training a Reinforcement Learning (RL) agent to play the classic Atari Breakout game using Double Deep Q-Networks (DDQN). (2023-09-13, Jupyter Notebook, 0KB, 下载0次)
尝试实现数据结构和算法-->;玩Jupyter笔记本、数据集和Scikit Learn
Me trying to implement Data Structures and Algorithms --> Playing with Jupyter notebooks, datasets and Scikit-Learn (2023-02-18, Jupyter Notebook, 0KB, 下载0次)
OsuLearn,尝试使用机器学习创建一个学习如何玩osu的神经网络!就像回放中的人类...
An attempt at using machine learning to create a neural network that learns how to play osu! like a human from replay data (2021-03-21, Jupyter Notebook, 1553KB, 下载0次)
cs231n卷积神经网络解决方案,斯坦福大学教授的视觉识别cs231n课程的分配解决方案。2017年春季的解决方案针对bo...
Assignment solutions for the CS231n course taught by Stanford on visual recognition. Spring 2017 solutions are for both deep learning frameworks: TensorFlow and PyTorch. (2017-09-21, Jupyter Notebook, 31719KB, 下载0次)
机器学习专业化课程,包含斯坦福大学和Deeplearning.ai公司关于机器学习专业的解决方案和注意事项...
Contains Solutions and Notes for the Machine Learning Specialization By Stanford University and Deeplearning.ai - Coursera (2022) by Prof. Andrew NG (2023-03-26, Jupyter Notebook, 51981KB, 下载0次)
csgo冲击评级,《反恐精英:全球进攻》的概率玩家评级系统,由机器学习提供支持,
A probabilistic player rating system for Counter Strike: Global Offensive,
powered by machine learning
, (2023-02-25, Jupyter Notebook, 2227KB, 下载0次)
存储库,包含用于构建、评估和解释Dota 2团队胜利预测模型的代码。提交至第16届AAAI人工智能与互动数字娱乐大会人工智能评估轨道-AIIDE 2020
Repository with code for building, evaluating and explaining Dota 2 prediction
models for team victory. Submitted to the artifact evaluation track of the
16th AAAI Conference on Artificial Intelligence and Interactive Digital
Entertainment - AIIDE 2020
, (2020-09-02, Jupyter Notebook, 439KB, 下载0次)
我对基于斯坦福CS231n的UdelaR深度学习课程第二项作业的解决方案。
My solution to the 2nd assignment of UdelaR s Deep Learning course, based on
Stanford CS231n.
, (2017-03-31, Jupyter Notebook, 882KB, 下载0次)