首页/论文/1707.03497

arXiv 1707.034972017-07cs.AIcs.LG

Value Prediction Network

University of Michigan（密歇根大学）；Google Brain（谷歌大脑）

Junhyuk Oh, Satinder Singh, Honglak Lee

备注：: NIPS 2017

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

英文摘要相关论文

英文摘要：

This paper proposes a novel deep reinforcement learning (RL) architecture, called Value Prediction Network (VPN), which integrates model-free and model-based RL methods into a single neural network. In contrast to typical model-based RL methods, VPN learns a dynamics model whose abstract states are trained to make option-conditional predictions of future values (discounted sum of rewards) rather than of future observations. Our experimental results show that VPN has several advantages over both model-free and model-based baselines in a stochastic environment where careful planning is required but building an accurate observation-prediction model is difficult. Furthermore, VPN outperforms Deep Q-Network (DQN) on several Atari games even with short-lookahead planning, demonstrating its potential as a new way of learning a good state representation.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

Just Propagate：面向链路预测的矩阵分解、网络嵌入与LightGCN统一框架

Just Propagate: Unifying Matrix Factorization, Network Embedding, and LightGCN for Link Prediction

针对链路预测领域缺乏对不同模型通用认知的问题，本文提出涵盖矩阵分解、代表性网络嵌入与图神经网络方法的统一框架，通过初步分析揭示关键设计因素，为方法创新提供启发。

2024-10-26cs.AIcs.LG

DynACPD Embedding Algorithm for Prediction Tasks in Dynamic Networks

Indiana University（印第安纳大学）

Classical network embeddings create a low dimensional representation of the learned relationships between features across nodes. Such embeddings are important for tasks such as link prediction and node classification. In the current paper, we consider low dimensional embeddings of dynamic networks, that is a family of time varying networks where there exist both temporal and spatial link relationships between nodes. We present novel embedding methods for a dynamic network based on higher order tensor decompositions for tensorial representations of the dynamic network. In one sense, our embeddi…

2021-03-12cs.AIcs.LG

Personalized Survival Prediction with Contextual Explanation Networks

Carnegie Mellon University（卡内基梅隆大学）

Accurate and transparent prediction of cancer survival times on the level of individual patients can inform and improve patient care and treatment practices. In this paper, we design a model that concurrently learns to accurately predict patient-specific survival distributions and to explain its predictions in terms of patient attributes such as clinical tests or assessments. Our model is flexible and based on a recurrent network, can handle various modalities of data including temporal measurements, and yet constructs and uses simple explanations in the form of patient- and time-specific line…

2018-01-30cs.AIcs.LG

压缩值预测用于学习增强的度量任务系统

Compressing Value Predictions for Learning-Augmented Metrical Task Systems

Huazhong University of Science and Technology（华中科技大学）

针对度量任务系统，提出地标压缩值预测方法，仅预测少量地标值并通过Lipschitz扩展重建其余值，实现加性超额成本上界，并证明匹配下界及学习保证。

2026-09-29cs.AIcs.GTcs.LG

Dynamic Prediction Length for Time Series with Sequence to Sequence Networks

Northwestern University（西北大学）

Recurrent neural networks and sequence to sequence models require a predetermined length for prediction output length. Our model addresses this by allowing the network to predict a variable length output in inference. A new loss function with a tailored gradient computation is developed that trades off prediction accuracy and output length. The model utilizes a function to determine whether a particular output at a time should be evaluated or not given a predetermined threshold. We evaluate the model on the problem of predicting the prices of securities. We find that the model makes longer pre…

2019-08-18cs.AIcs.LGstat.ML

Prediction Algorithm for Heat Demand of Science and Technology Topics Based on Time Convolution Network

Beijing University of Posts and Telecommunications（北京邮电大学）

Thanks to the rapid development of deep learning, big data analysis technology is not only widely used in the field of natural language processing, but also more mature in the field of numerical prediction. It is of great significance for the subject heat prediction and analysis of science and technology demand data. How to apply theme features to accurately predict the theme heat of science and technology demand is the core to solve this problem. In this paper, a prediction method of subject heat of science and technology demand based on time convolution network (TCN) is proposed to obtain th…

2022-03-21cs.AIcs.IRcs.LG

更多相关论文收起更多论文

A Review of Network Traffic Analysis and Prediction Techniques

North Maharashtra University（北马哈拉施特拉大学）

Analysis and prediction of network traffic has applications in wide comprehensive set of areas and has newly attracted significant number of studies. Different kinds of experiments are conducted and summarized to identify various problems in existing computer network applications. Network traffic analysis and prediction is a proactive approach to ensure secure, reliable and qualitative network communication. Various techniques are proposed and experimented for analyzing network traffic including neural network based techniques to data mining techniques. Similarly, various Linear and non-linear…

2015-07-27cs.AIcs.NI

基于高斯贝叶斯网络的轨道交通全局运输能力风险预测方法

A Global Transport Capacity Risk Prediction Method for Rail Transit Based on Gaussian Bayesian Network

Tsinghua University（清华大学）

针对轨道交通承载能力与客流需求不匹配的运输能力风险预测问题，提出一种基于线性高斯贝叶斯网络的可解释预测方法，利用三层结构仿真模型获取数据并结合MLE进行参数学习，仿真验证了其有效性。

2023-08-03cs.AI

Erratum: Link prediction in drug-target interactions network using similarity indices

Computer Laboratory, University of Cambridge（剑桥大学计算机实验室）

Background: In silico drug-target interaction (DTI) prediction plays an integral role in drug repositioning: the discovery of new uses for existing drugs. One popular method of drug repositioning is network-based DTI prediction, which uses complex network theory to predict DTIs from a drug-target network. Currently, most network-based DTI prediction is based on machine learning methods such as Restricted Boltzmann Machines (RBM) or Support Vector Machines (SVM). These methods require additional information about the characteristics of drugs, targets and DTIs, such as chemical structure, genome…

2017-11-01cs.AI

Heterogeneous Graph based Deep Learning for Biomedical Network Link Prediction

Global Health Drug Discovery Institute（全球健康药物研发中心）

Multi-scale biomedical knowledge networks are expanding with emerging experimental technologies that generates multi-scale biomedical big data. Link prediction is increasingly used especially in bipartite biomedical networks to identify hidden biological interactions and relationshipts between key entities such as compounds, targets, gene and diseases. We propose a Graph Neural Networks (GNN) method, namely Graph Pair based Link Prediction model (GPLP), for predicting biomedical network links simply based on their topological interaction information. In GPLP, 1-hop subgraphs extracted from kno…

2022-02-24cs.AIcs.IRcs.LG

通过大语言模型（LLM）初始化节点特征增强量子计算语义网络中的未来链路预测

Enhancing Future Link Prediction in Quantum Computing Semantic Networks through LLM-Initiated Node Features

Brookhaven National Laboratory（布鲁克海文国家实验室）

本研究针对量子计算语义网络的链路预测任务，提出用LLM初始化节点特征以优化图神经网络节点表征的方法，经多种模型验证，效果优于传统节点嵌入技术，可减少人工特征构建成本。

2024-10-05cs.AIcs.CLcs.LG

使用Informer网络进行股票与市场指数预测

Stock and market index prediction using Informer network

Shenzhen Ping An Integrated Financial Services Co., Ltd.（深圳平安综合金融服务有限公司）

针对分钟尺度日内预测的挑战，本文提出基于Informer网络进行股票与市场指数预测，通过多频率多数据集实验证明其优于LSTM、Transformer和BERT，并验证了全局时间戳机制与迁移学习能力的有效性，适用于实际交易。

2023-05-22cs.AIq-fin.ST

Price Updating in Combinatorial Prediction Markets with Bayesian Networks

Yahoo! Research（雅虎研究院）；Duke University（杜克大学）

To overcome the #P-hardness of computing/updating prices in logarithm market scoring rule-based (LMSR-based) combinatorial prediction markets, Chen et al. [5] recently used a simple Bayesian network to represent the prices of securities in combinatorial predictionmarkets for tournaments, and showed that two types of popular securities are structure preserving. In this paper, we significantly extend this idea by employing Bayesian networks in general combinatorial prediction markets. We reveal a very natural connection between LMSR-based combinatorial prediction markets and probabilistic belief…

2012-02-14cs.AIcs.GT

On the Prediction Network Architecture in RNN-T for ASR

Nuance Communications, Inc.（Nuance通讯公司）

RNN-T models have gained popularity in the literature and in commercial systems because of their competitiveness and capability of operating in online streaming mode. In this work, we conduct an extensive study comparing several prediction network architectures for both monotonic and original RNN-T models. We compare 4 types of prediction networks based on a common state-of-the-art Conformer encoder and report results obtained on Librispeech and an internal medical conversation data set. Our study covers both offline batch-mode and online streaming scenarios. In contrast to some previous works…

2022-06-29cs.AIeess.AS

From Imitation to Prediction, Data Compression vs Recurrent Neural Networks for Natural Language Processing

Universidad de Buenos Aires（布宜诺斯艾利斯大学）

In recent studies [1][13][12] Recurrent Neural Networks were used for generative processes and their surprising performance can be explained by their ability to create good predictions. In addition, data compression is also based on predictions. What the problem comes down to is whether a data compressor could be used to perform as well as recurrent neural networks in natural language processing tasks. If this is possible,then the problem comes down to determining if a compression algorithm is even more intelligent than a neural network in specific tasks related to human language. In our journ…

2017-05-01cs.AIcs.CLcs.IT

Perception as prediction using general value functions in autonomous driving applications

Huawei Technologies Canada, Ltd.（加拿大华为技术有限公司）；University of Alberta（阿尔伯塔大学）

We propose and demonstrate a framework called perception as prediction for autonomous driving that uses general value functions (GVFs) to learn predictions. Perception as prediction learns data-driven predictions relating to the impact of actions on the agent's perception of the world. It also provides a data-driven approach to predict the impact of the anticipated behavior of other agents on the world without explicitly learning their policy or intentions. We demonstrate perception as prediction by learning to predict an agent's front safety and rear safety with GVFs, which encapsulate antici…

2020-01-24cs.AIcs.ROcs.SY