-
강화학습 프로젝트 참고 자료AI/Reinforcement Learning 2021. 11. 6. 15:58728x90
https://data-newbie.tistory.com/648?category=776421
[RL] 강화학습 알고리즘 baseline 코드 URL
github.com/openai/baselines/tree/master/baselines openai/baselines OpenAI Baselines: high-quality implementations of reinforcement learning algorithms - openai/baselines github.com stable-baselines...
data-newbie.tistory.com
https://www.kaggle.com/osbornep/-reinforcement-learning-from-scratch-in-python
Reinforcement Learning from Scratch in Python
Beginner's Guide to Finding the Optimal Actions of a Defined Environment
www.kaggle.com
https://www.kaggle.com/deepakdeepu8978/drug-indications-drug-engineering-with-ai
Drug Indications (Drug Engineering with AI)
The computer brain versus the human brain for drug design
www.kaggle.com
https://www.kaggle.com/iamhungundji/covid19-symptoms-checker
COVID-19 Symptoms Checker
Predict whether someone has coronavirus or not?
www.kaggle.com
인공지능(AI) 강화학습, 고객 여정 최적화의 필수 요소로 자리잡다!
기업의 마케팅 전략도 인공지능(AI), 사물인터넷(IoT)과 같은 혁신적인 기술이 등장하며 함께 발전하고 있습니다.
blogs.sas.com
http://insightcampus.co.kr:9090/insightcommunity/?mod=document&uid=12704
https://saedu.naver.com/help/faq/ncc/view.naver?faqSeq=171
네이버 광고
saedu.naver.com
https://www.youtube.com/watch?v=0abkhP8X_9g
http://insightcampus.co.kr:9090/insightcommunity/?mod=document&uid=12704
https://analyticsindiamag.com/ad-click-through-rate-ctr-prediction-using-reinforcement-learning/
Ad Click-Through-Rate (CTR) Prediction using Reinforcement Learning
Ad Click-Through-Rate (CTR) Prediction using Reinforcement Learning - Upper Confidence Bound implemented in python for Web Ads
analyticsindiamag.com
https://jisoo-coding.tistory.com/27
[추천시스템]DRN: A Deep Reinforcement Learning Framework for News Recommendation
논문 링크 http://www.personal.psu.edu/~gjz5038/paper/www2018_reinforceRec/www2018_reinforceRec.pdf 불러오는 중입니다... 딥 러닝 모델을 이용해 뉴스 추천을 하는 데는 세 가지 취약점이 있다. 첫 번째는..
jisoo-coding.tistory.com
GitHub - guyulongcs/Awesome-Deep-Reinforcement-Learning-Papers-for-Search-Recommendation-Advertising: Awesome Deep Reinforcement
Awesome Deep Reinforcement Learning papers for industrial Search, Recommendation and Advertising. - GitHub - guyulongcs/Awesome-Deep-Reinforcement-Learning-Papers-for-Search-Recommendation-Adverti...
github.com
추천 시스템 기본 - 협업 필터링(Collaborative Filtering) - ②
*크롬으로 보시는 걸 추천드립니다* 대표적 추천 시스템인 협업 필터링(Collaborative Filtering) 중 Memory-Based Approach에 대해서 다루어보았습니다 https://kmhana.tistory.com/31?category=882777 Have A Ni..
kmhana.tistory.com
https://m.blog.naver.com/nilsine11202/221912267111
[추천시스템] 2. Multi-Armed Bandit (MAB)
어떤 슬롯머신이 어떤 수익률을 가지는지 모를 때, 탐색(Exploration)과 활용(Exploitation)을 적절히 사...
blog.naver.com
http://doc.mindscale.kr/km/data_mining/11.html
http://doc.mindscale.kr/km/data_mining/11.html
11. A/B 테스팅과 '여러 팔 강도' 문제 11.1. A/B 테스팅 최근 인터넷을 이용한 상거래가 활발해지면서 'A/B 테스팅'이라는 아이디어가 인기를 얻게 되었다. A/B 테스팅은 메뉴, 문구, 광고 등을 고객마
doc.mindscale.kr
https://biz.chosun.com/site/data/html_dir/2017/07/31/2017073100012.html
[미디어 혁신가] "카카오 AI 루빅스, 계속 진화… 열독한 기사 골라서 추천"
미디어 혁신가 카카오 AI 루빅스, 계속 진화 열독한 기사 골라서 추천
biz.chosun.com
https://sungkee-book.tistory.com/14
[추천시스템] Multi-Armed Bandit
MAB의 등장 배경은 카지노에 있는 슬롯머신과 관련있다. Bandit은 슬롯머신을, Arm이란 슬롯머신의 손잡이를 의미한다. 카지노에는 다양한 슬롯머신 기계들이 구비되어 있다. 고객들은 경험적으로
sungkee-book.tistory.com
https://tech.kakao.com/2021/06/25/kakao-ai-recommendation-01/
카카오 AI추천 : 토픽 모델링과 MAB를 이용한 카카오 개인화 추천
글 작성에는 추천팀 sasha.k와 marv.20가 함께해 주셨습니다. 머신러닝에 대한 기초 지식이 있고, 추천 알고리즘에 관심이 있는 분들에게 카카오 추천팀이 개인화 추천 기술을 활용하는 방법에 대해
tech.kakao.com
https://tech.kakao.com/2021/10/18/collaborative-filtering/
카카오 AI추천 : 협업 필터링 모델 선택 시의 기준에 대하여
안녕하세요. 카카오 추천팀의 hee.yoon입니다. 여기에서는 협업 필터링(Collaborative Filtering, CF)이 무엇인지를 먼저 살펴 본 다음, 협업 필터링을 활용해 추천 시스템을 개발할 때 중요하게 고려해야
tech.kakao.com
Thompson Sampling(톰슨 샘플링)
중국 블로그 : http://x-algo.cn/index.php/2016/12/15/ee-problem-and-bandit-algorithm-for-recommender-systems/ 시뮬레이터 : https://learnforeverlearn.com/bandits/ Python Sample code(파이썬 샘플 코드..
sijoo.tistory.com
https://www.kaggle.com/c/avazu-ctr-prediction/data
Click-Through Rate Prediction | Kaggle
www.kaggle.com
https://www.kaggle.com/c/avito-context-ad-clicks/data
Avito Context Ad Clicks | Kaggle
www.kaggle.com
https://analyticsindiamag.com/ad-click-through-rate-ctr-prediction-using-reinforcement-learning/
Ad Click-Through-Rate (CTR) Prediction using Reinforcement Learning
Ad Click-Through-Rate (CTR) Prediction using Reinforcement Learning - Upper Confidence Bound implemented in python for Web Ads
analyticsindiamag.com
https://www.kaggle.com/farhanmd29/predicting-customer-ad-clicks/notebook
Predicting customer ad clicks
Explore and run machine learning code with Kaggle Notebooks | Using data from Advertising
www.kaggle.com
https://lsjsj92.tistory.com/568
파이썬으로 추천 시스템(recommendation system) 구현해보기 - collaborative filtering
포스팅 개요 해당 글에 대한 코드는 아래 github 링크에 전부 올려두었습니다. https://github.com/lsjsj92/recommender_system_with_Python/blob/master/003.%20recommender%20system%20basic%20with%20Python%20..
lsjsj92.tistory.com
https://www.kaggle.com/shivamb/netflix-shows
Netflix Movies and TV Shows
Listings of movies and tv shows on Netflix - Regularly Updated
www.kaggle.com
https://sungkee-book.tistory.com/14
[추천시스템] Multi-Armed Bandit
MAB의 등장 배경은 카지노에 있는 슬롯머신과 관련있다. Bandit은 슬롯머신을, Arm이란 슬롯머신의 손잡이를 의미한다. 카지노에는 다양한 슬롯머신 기계들이 구비되어 있다. 고객들은 경험적으로
sungkee-book.tistory.com
https://jisoo-coding.tistory.com/27
[추천시스템]DRN: A Deep Reinforcement Learning Framework for News Recommendation
논문 링크 http://www.personal.psu.edu/~gjz5038/paper/www2018_reinforceRec/www2018_reinforceRec.pdf 불러오는 중입니다... 딥 러닝 모델을 이용해 뉴스 추천을 하는 데는 세 가지 취약점이 있다. 첫 번째는..
jisoo-coding.tistory.com
https://github.com/chris-chris/bandits-baseline/blob/master/beta.py
GitHub - chris-chris/bandits-baseline
Contribute to chris-chris/bandits-baseline development by creating an account on GitHub.
github.com
https://www.kaggle.com/getting-started/105530
📜Recommandation Systems tutorials📜 | Data Science and Machine Learning
📜Recommandation Systems tutorials📜.
www.kaggle.com
https://medium.com/ibm-data-ai/recommendation-systems-using-reinforcement-learning-de6379eecfde
Recommendation Systems using Reinforcement Learning
Recommendation system models have become one of the most important aspects in customer retention.
medium.com
https://cseweb.ucsd.edu//~jmcauley/datasets.html
Recommender Systems Datasets
--> Recommender Systems and Personalization Datasets Julian McAuley, UCSD Description This page contains a collection of datasets that have been collected for research by our lab. Datasets contain the following features: user/item interactions star ratings
cseweb.ucsd.edu
https://github.com/lsjsj92/recommender_system_with_Python
GitHub - lsjsj92/recommender_system_with_Python: recommender system tutorial with Python
recommender system tutorial with Python. Contribute to lsjsj92/recommender_system_with_Python development by creating an account on GitHub.
github.com
Deep Reinforcement Learning for List-wise Recommendations
https://github.com/egipcy/LIRD/blob/master/LIRD.ipynb
GitHub - egipcy/LIRD: Deep Reinforcement Learning for Movies Recommendation System
Deep Reinforcement Learning for Movies Recommendation System - GitHub - egipcy/LIRD: Deep Reinforcement Learning for Movies Recommendation System
github.com
https://arxiv.org/abs/1801.00209
Deep Reinforcement Learning for List-wise Recommendations
Recommender systems play a crucial role in mitigating the problem of information overload by suggesting users' personalized items or services. The vast majority of traditional recommender systems consider the recommendation procedure as a static process an
arxiv.org
https://github.com/luozachary/drl-rec
GitHub - luozachary/drl-rec: Deep reinforcement learning for recommendation system
Deep reinforcement learning for recommendation system - GitHub - luozachary/drl-rec: Deep reinforcement learning for recommendation system
github.com
https://github.com/PierreGe/RL-movie-recommender
GitHub - PierreGe/RL-movie-recommender: The purpose of our research is to study reinforcement learning approaches to building a
The purpose of our research is to study reinforcement learning approaches to building a movie recommender system. We formulate the problem of interactive recommendation as a contextual multi-armed ...
github.com
https://github.com/JianGuanTHU/IRecGAN
GitHub - JianGuanTHU/IRecGAN: Implementation for our paper in NeurIPS 2019
Implementation for our paper in NeurIPS 2019. Contribute to JianGuanTHU/IRecGAN development by creating an account on GitHub.
github.com
728x90'AI > Reinforcement Learning' 카테고리의 다른 글
Chapter 03) Model-based Planning (0) 2023.04.12 Chapter 02) Markov Decision Process (0) 2023.04.12 Chapter 01) Reinforcement Learning Overview (1) 2023.04.11