paper-with-me

홈 › Papers

Meta-learning of Sequential Strategies

2019-05-08 · Pedro A. Ortega, Jane. X. Wang, Mark Rowland, Tim Genewein, Zeb Kurth-Nelson, Razvan Pascanu, Nicolas Heess, Joel Veness, Alex Pritzel, Pablo Sprechmann, Siddhant M. Jayakumar, Tom McGrath, Kevin Miller, Mohammad Azar, Ian Osband, Neil Rabinowitz, András György, Silvia Chiappa, Simon Osindero, Yee Whye Teh, Hado Van Hasselt, Nando de Freitas, Matthew Botvinick, Shane Legg

In this report we review memory-based meta-learning as a tool for building sample-efficient strategies that learn from past experience to adapt to any task within a target class. Our goal is to equip the reader with the conceptual foundations of this tool for building new, scalable agents that operate on broad domains. To do so, we present basic algorithmic templates for building near-optimal predictors and reinforcement learners which behave as if they had a probabilistic model that allowed them to efficiently exploit task structure. Furthermore, we recast memory-based meta-learning within a Bayesian framework, showing that the meta-learned strategies are near-optimal because they amortize Bayes-filtered data, where the adaptation is implemented in the memory dynamics as a state-machine of sufficient statistics. Essentially, memory-based meta-learning translates the hard problem of probabilistic sequential inference into a regression problem.

📄 PDF Abstract BibTeX arXiv:1905.03030

Code (0)

등록된 구현이 없습니다.

Tasks

Meta-Learning

Similar Papers 제목 키워드 기반

Meta-optimized Joint Generative and Contrastive Learning for Sequential Recommendation

2023-10-21 · Yongjing Hao, Pengpeng Zhao, Junhua Fang, Jianfeng Qu 외

Sequential Recommendation (SR) has received increasing attention due to its ability to capture user dynamic preferences. Recently, Contrastive Learning (CL) provides an effective approach for sequential recommendation by…

Contrastive LearningSequential Recommendation

Meta-AAD: Active Anomaly Detection with Deep Reinforcement Learning

2020-09-16 · Daochen Zha, Kwei-Herng Lai, Mingyang Wan, Xia Hu

High false-positive rate is a long-standing challenge for anomaly detection algorithms, especially in high-stake applications. To identify the true anomalies, in practice, analysts or domain experts will be employed to i…

Anomaly DetectionDeep Reinforcement Learningreinforcement-learningReinforcement Learning+2

Learning an Adaptive Meta Model-Generator for Incrementally Updating Recommender Systems

2021-11-08 · Danni Peng, Sinno Jialin Pan, Jie Zhang, AnXiang Zeng

Recommender Systems (RSs) in real-world applications often deal with billions of user interactions daily. To capture the most recent trends effectively, it is common to update the model incrementally using only the newly…

Computational EfficiencyRecommendation Systems

Toward Universal Medical Image Registration via Sharpness-Aware Meta-Continual Learning

2024-06-25 · Bomin Wang, Xinzhe Luo, Xiahai Zhuang

Current deep learning approaches in medical image registration usually face the challenges of distribution shift and data collection, hindering real-world deployment. In contrast, universal medical image registration aim…

Continual LearningImage RegistrationMedical Image RegistrationMeta-Learning

Deep Interactive Bayesian Reinforcement Learning via Meta-Learning

2021-01-11 · Luisa Zintgraf, Sam Devlin, Kamil Ciosek, Shimon Whiteson 외

Agents that interact with other agents often do not know a priori what the other agents' strategies are, but have to maximise their own online return while interacting with and learning about others. The optimal adaptive…

Meta-Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)