paper link: https://arxiv.org/abs/1606.03966
Contextual Bandit pipeline 을 구성할 때 어떻게 하면 기술 부채가 적어지는지에 대한 내용을 다루는 것 같음
1 min read
paper link: https://arxiv.org/abs/1606.03966
Contextual Bandit pipeline 을 구성할 때 어떻게 하면 기술 부채가 적어지는지에 대한 내용을 다루는 것 같음
Mortal MAB, Multi-Armed Bandit Related Mortal Multi Armed Bandit (2008) References papers.nips.cc/paper/2008/file/788d986905533aba051261497ecffcbb-Paper.pdf.
Links Paper link Abstract optimism principle 에 기반한 알고리즘은 문제에 대한 구조를 exploit 하는데 실패하여 점근적으로 suboptimal 결과를 보임 context 분포와 exploration policy 가 나눠지도록 (decoupled) regret lower...
Abstract Probability Ranking Principle 에 의하면 top-K items 을 greedy 하게 rank 하는것이 optimal 함 대신 Introduction This work investigates how the “equity of exposure” principle can be...
References www.chenshouyuan.com/papers/sdm14.pdf .
paper Link: arxiv.org/pdf/1205.2606.pdf KWIK Linear Regression KWIK (Knows What It Knows) is a framework for studying supervised learning algorithms and was designed to unify...
Discussion Q-learning based offline 학습 방식이고, 모델도 무겁고.
Abstract 해결하려는 문제: 강화학습에서의 효율적인 exploration Randomized value functions offer a promising approach to efficient exploration with generalization, but existing algorithms are not...
References paper link: arxiv.org/pdf/2109.10665.pdf Reinforcement Learning based Recommender Systems: A Survey .
Empirical Evaluation: Live Experiments YouTube 에 SARSA-TS 알고리즘을 실험 candidate -> ranker 를 거치게 되는데, ranker 의 scoring 함수에서 사용하는 myopic(근시안적) engagement 측정값을 LTV estimate 로 변경함...
Paper link arxiv.org/abs/1812.07127 .