A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Filters
Meta-Q-Learning
[article]
2020
arXiv
pre-print
Preserved Fulltext
Other Versions
This paper introduces Meta-Q-Learning (MQL), a new off-policy algorithm for meta-Reinforcement Learning (meta-RL). MQL builds upon three simple ideas. ...
First, we show that Q-learning is competitive with state-of-the-art meta-RL algorithms if given access to a context variable that is a representation of the past trajectory. ...
Our second contribution is an off-policy meta-RL algorithm named Meta-Q-Learning (MQL) that builds upon the above result. ...
arXiv:1910.00125v2
fatcat:vv7o6dhce5grzfrcrqiqao42pq
Revisiting Meta-Learning as Supervised Learning
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
This view not only unifies meta-learning into an intuitive and practical framework but also allows us to transfer insights from supervised learning directly to improve meta-learning. ...
Recent years have witnessed an abundance of new publications and approaches on meta-learning. ...
Introduction Meta-learning, or learning to learn, is the sub-field of machine learning occupied with the search for the best An extended version of the paper titled "A Meta Understanding of Meta-Learning ...
arXiv:2002.00573v1
fatcat:f5fcejzwmrgbjp4pn64fvqp43a
Generating meta-learning tasks to evolve parametric loss for classification learning
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
In existing meta-learning approaches, learning tasks for training meta-models are usually collected from public datasets, which brings the difficulty of obtaining a sufficient number of meta-learning tasks ...
In this paper, we propose a meta-learning approach based on randomly generated meta-learning tasks to obtain a parametric loss for classification learning based on big data. ...
Meta-learning for few-shot learning In the field of supervised learning, existing meta-learning methods are mainly developed for few-shot learning. ...
arXiv:2111.10583v1
fatcat:zgbhmbuewrdahbmygu6gazczv4
Meta-Learning GNN Initializations for Low-Resource Molecular Property Prediction
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Meanwhile advances in meta-learning have enabled state-of-the-art performances in few-shot learning benchmarks, naturally prompting the question: Can meta-learning improve deep learning performance in ...
In this work, we assess the transferability of graph neural networks initializations learned by the Model-Agnostic Meta-Learning (MAML) algorithm - and its variants FO-MAML and ANIL - for chemical properties ...
Meta-Learning The same GGNN architecture as the baselines is used for all three meta-learning algorithms. ...
arXiv:2003.05996v2
fatcat:enugsgd27bbc7jvlfuxixkfedy
ST^2: Small-data Text Style Transfer via Multi-task Meta-Learning
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
In this work, we develop a meta-learning framework to transfer between any kind of text styles, including personal writing styles that are more fine-grained, share less content and have much smaller training ...
We define the shared model with parameters θ as a meta-learner. The data for each task is divided in to a support set D s and a query set D q . ...
Compared with other model-based meta-learning methods, modelagnostic meta-learning algorithm (MAML) utilizes only gradient information (Finn et al., 2017) . ...
arXiv:2004.11742v1
fatcat:j3tbgwdy4bhojmeu4sbu6zkope
Q-HeteLearn: A Progressive Learning approach for Classifying Meta-Paths in Heterogeneous Information Networks
2020
International Journal of Emerging Trends in Engineering Research
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
The concept of Q-HeteLearn which is a Progressive Learning technique is introduced to improve the swift traversal of the objects in the meta-paths and to classify them. ...
In this paper a novel approach called Q-HeteLearn a Progressive Learning method is introduced to classify the objects by traversing the meta-paths in the Heterogeneous Information Networks. ...
But a meta-path expands as new objects add to it and new relationships exist. Therefore, the Deep Q-Learning strategy is also used to compare Q-HeteLearn. ...
doi:10.30534/ijeter/2020/35832020
fatcat:m6xvtws7mzhyzb526w4eme57da
MICK: A Meta-Learning Framework for Few-shot Relation Classification with Little Training Data
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
We also propose a few-shot learning framework for relation classification, which is particularly powerful when the training data is very small. ...
Given an encoded query instance Q = (E q , r q ) where r q is to be predicted, class matching aims to match r q with some relation class r i ∈ R. ...
Meta-learning is a popular method for few-shot learning and is widely investigated in computer vision (CV). ...
arXiv:2004.14164v1
fatcat:u65ygi6ahjekrbdx35pomhtqqe
Fingerprinting diverse nanoporous materials for optimal hydrogen storage conditions using meta-learning
2021
Science Advances
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Using data obtained from high-throughput Monte Carlo simulations for zeolites, metal-organic frameworks, and hyper–cross-linked polymers, we develop a meta-learning model that jointly predicts the adsorption ...
Meta-learning gives higher accuracy and improved generalization compared to fitting a model separately to each material and allows us to identify the optimal hydrogen storage temperature with the highest ...
Meta-learning for predicting gas adsorption loading, q, in NPMs. (A) A meta-learning problem setup. ...
doi:10.1126/sciadv.abg3983
pmid:34290094
fatcat:xfmb7jtfsbb7tarezbiabpafim
Meta-game Equilibrium for Multi-agent Reinforcement Learning
[chapter]
2004
Lecture Notes in Computer Science
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2005; you can also visit the original URL.
The file type is application/pdf.
This paper proposes a multi-agent Q-learning algorithm called meta-game-Q learning that is developed from the meta-game equilibrium concept. ...
We use the repeated prisoner's dilemma example to empirically demonstrate that the algorithm converges to meta-game equilibrium. ...
A template for meta-game-Q reinforcement learning is presented in Table 2 . ...
doi:10.1007/978-3-540-30549-1_81
fatcat:7z2k6nlsxngu5igw7kl4xc6o5a
Meta-Learning Divergences of Variational Inference
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
In this paper we propose a meta-learning algorithm to learn the divergence metric suited for the task of interest, automating the design of VI methods. ...
In addition, we learn the initialization of the variational parameters without additional cost when our method is deployed in the few-shot learning scenarios. ...
During meta-testing, a new task is sampled from p(T ), and the learned divergence D η is used to optimize the variational distribution q φ . ...
arXiv:2007.02912v2
fatcat:4zzyeegb3bb6hefcezwyr7hyeq
Adaptive-Control-Oriented Meta-Learning for Nonlinear Systems
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Our key insight is that we can better prepare the controller for deployment with control-oriented meta-learning of features in closed-loop simulation, rather than regression-oriented meta-learning of features ...
Specifically, we meta-learn the adaptive controller with closed-loop tracking simulation as the base-learner and the average tracking error as the meta-objective. ...
Meta-Learning Meta-learning is the tool we use to inject the downstream adaptive control application into offline learning from data. ...
arXiv:2103.04490v2
fatcat:uf7fzau2qjc6fk2oco3tjp73ku
Learning State-Dependent Losses for Inverse Dynamics Learning
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
In this work, we propose to apply meta-learning to learn structured, state-dependent loss functions during a meta-training phase. ...
We then replace standard losses with our learned losses during online adaptation tasks. ...
Meta-Learning Dynamics Models There has also been research in meta-learning with a focus on meta-learning dynamics models, either with fast finetuning [26] or with online learning of a memory learning ...
arXiv:2003.04947v3
fatcat:c4l3qa4zqndedkyfijgzztoiai
Meta-Learning by Adjusting Priors Based on Extended PAC-Bayes Theory
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
We present a framework for meta-learning that is based on generalization error bounds, allowing us to extend various PAC-Bayes bounds to meta-learning. ...
In meta-learning an agent extracts knowledge from observed tasks, aiming to facilitate learning of novel future tasks. ...
Meta-Learning Problem Formulation The meta-learning problem formulation follows Pentina & Lampert (2014) . ...
arXiv:1711.01244v8
fatcat:uvbegjw6erezjebbinjrrejzpe
Meta-Learning without Memorization
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
In some domains, this makes meta-learning entirely inapplicable. ...
Meta-learning has emerged as a promising technique for leveraging data from previous tasks to enable efficient learning of new tasks. ...
Complete memorization in meta-learning is when the learned model ignores the task training data such that I(ŷ * ; D|x * , θ) = 0 (i.e., q(ŷ * |x * , θ, D) = q(ŷ * |x * , θ) = E D |x * [q(ŷ * |x * , θ, ...
arXiv:1912.03820v3
fatcat:dsunnq42zvdsxa372bdtkn56yi
Off-Policy Meta-Reinforcement Learning with Belief-based Task Inference
2022
IEEE Access
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
The agent learns a belief model over the task embedding space and trains a belief-conditional policy and Q-function. ...
To alleviate this problem, we propose a novel off-policy meta-RL method, embedding learning and uncertainty evaluation (ELUE). ...
LEARNING BELIEF-CONDITIONAL POLICY AND Q-FUNCTION In this section, we introduce how the ELUE agent learns a belief-conditional policy and Q-function in meta-training. ...
doi:10.1109/access.2022.3170582
fatcat:nkkav52wenbhrontkzmewehw7u
« Previous
Showing results 1 — 15 out of 87,191 results