Filters








5,592 Hits in 2.5 sec

A Survey on Reinforcement Learning for Recommender Systems [article]

Yuanguo Lin, Yong Liu, Fan Lin, Pengcheng Wu, Wenhua Zeng, Chunyan Miao
2021 arXiv   pre-print
Recently, Reinforcement Learning (RL) based recommender systems have become an emerging research topic.  ...  It often surpasses traditional recommendation models even most deep learning-based methods, owing to its interactive nature and autonomous learning ability.  ...  The conversation action is performed by a policy network, which is optimized via the REINFORCE algorithm.  ... 
arXiv:2109.10665v1 fatcat:whrqgxcb4fa53omquvpy6nitjm

Deep Conversational Recommender Systems: A New Frontier for Goal-Oriented Dialogue Systems [article]

Dai Hoang Tran, Quan Z. Sheng, Wei Emma Zhang, Salma Abdalla Hamad, Munazza Zaib, Nguyen H. Tran, Lina Yao, Nguyen Lu Dang Khoa
2020 arXiv   pre-print
Unlike traditional recommender systems with content-based and collaborative filtering approaches, CRS learns and models user's preferences through interactive dialogue conversations.  ...  In recent years, the emerging topics of recommender systems that take advantage of natural language processing techniques have attracted much attention, and one of their applications is the Conversational  ...  Deep Policy Network Deep policy network is a straight-forward usage of reinforcement learning to maximize the reward of a SWM action based on current dialogue state.  ... 
arXiv:2004.13245v1 fatcat:byx4zsdshvc5fc3hjs7acoi5li

Multi-Choice Questions based Multi-Interest Policy Learning for Conversational Recommendation [article]

Yiming Zhang, Lingfei Wu, Qi Shen, Yitong Pang, Zhihua Wei, Fangli Xu, Bo Long, Jian Pei
2021 arXiv   pre-print
To effectively cope with the new CRS learning setting, in this paper, we propose a novel learning framework namely, Multi-Choice questions based Multi-Interest Policy Learning .  ...  Conversational recommendation system (CRS) is able to obtain fine-grained and dynamic user preferences based on interactive dialogue. Previous CRS assumes that the user has a clear target item.  ...  UNICORN [8] proposes a unified reinforcement learning framework based on dynamic weighted graph for MCR, which unifies three decision-making processes.  ... 
arXiv:2112.11775v1 fatcat:bjs7io6un5a67dh3cb36qg7wnm

Neural Approaches to Conversational AI

Jianfeng Gao, Michel Galley, Lihong Li
2018 Proceedings of ACL 2018, Tutorial Abstracts  
This tutorial surveys neural approaches to conversational AI that were developed in the last few years.  ...  We group conversational systems into three categories: (1) question answering agents, (2) taskoriented dialogue agents, and (3) social bots.  ...  breakthroughs in deep learning (DL) and reinforcement learning (RL) are applied to conversational AI.  ... 
doi:10.18653/v1/p18-5002 dblp:conf/acl/GaoGL18 fatcat:7llxwuntafh4fcjj4ia3tm642a

Reinforcement Learning over Knowledge Graphs for Explainable Dialogue Intent Mining

Kai Yang, Xinyu Kong, Yafang Wang, Jie Zhang, Gerard De Melo
2020 IEEE Access  
Finally, we consider a wide range of recently proposed knowledge graph-based recommender systems as baselines, mostly based on deep reinforcement learning and our method performs best.  ...  We rely on policy-guided reinforcement learning to identify paths in a graph to confirm concrete paths of inference that serve as interpretable explanations.  ...  Besides, reinforcement learning can also be used in automated knowledge base completion and knowledge aware conversation generation.  ... 
doi:10.1109/access.2020.2991257 fatcat:wtgscficrzdozp25zy2arysxpi

Learning TSP Requires Rethinking Generalization [article]

Chaitanya K. Joshi, Quentin Cappart, Louis-Martin Rousseau, Thomas Laurent
2021 arXiv   pre-print
While state-of-the-art Machine Learning approaches perform closely to classical solvers when trained on trivially small sizes, they are unable to generalize the learnt policy to larger instances of practical  ...  Towards leveraging transfer learning to solve large-scale TSPs, this paper identifies inductive biases, model architectures and learning algorithms that promote generalization to instances larger than  ...  trained on 12.8 Million TSP instances via reinforcement learning.  ... 
arXiv:2006.07054v3 fatcat:fsxtrv2tzveabftlxzjuzpdura

Neural Approaches to Conversational AI

Jianfeng Gao, Michel Galley, Lihong Li
2019 Foundations and Trends in Information Retrieval  
"Hybrid Reinforcement/Supervised Learning of Dialogue Policies from Fixed Data Sets". Computational Linguistics. 34(4): 487-511. Table 1 . 1 : 11 Reinforcement Learning for Dialogue.  ...  "On-line Policy Optimisation of Bayesian Spoken Dialogue Systems via Human Interaction".  ... 
doi:10.1561/1500000074 fatcat:5ou22zmnq5ghjnkqmbxbfkurhu

Deep Hierarchical Reinforcement Learning Based Recommendations via Multi-goals Abstraction [article]

Dongyang Zhao, Liang Zhang, Bo Zhang, Lizhou Zheng, Yongjun Bao, Weipeng Yan
2019 arXiv   pre-print
To solve the inherent problem in hierarchical reinforcement learning, we propose a novel deep hierarchical reinforcement learning algorithm via multi-goals abstraction (HRL-MG).  ...  To tackle this challenge, we propose a deep hierarchical reinforcement learning based recommendation framework, which consists of two components, i.e., high-level agent and low-level agent.  ...  The deep reinforcement learning (DRL) based methods overcome this problem via interacting with users in real time and dynamically adjust the recommendation strategies.  ... 
arXiv:1903.09374v1 fatcat:pp55xrgzwravdmtcw6o45jop7q

Gaussian process decentralized data fusion meets transfer learning in large-scale distributed cooperative perception

Ruofei Ouyang, Bryan Kian Hsiang Low
2019 Autonomous Robots  
a Blend of Goal-Based and Procedural Tasks Aaron Mininger*, John Laird Interpretable Graph-Based Semi-Supervised Learning via Flows Raif Rustamov*, James Klosowski Interpreting CNN Knowledge Via An Explanatory  ...  Feature Extraction for Human Action Recognition Yang Du, Chunfeng Yuan*, Weiming Hu, Hao Yang Hierarchical Policy Search via Return-Weighted Density Estimation Takayuki Osa*, Masashi Sugiyama Hierarchical  ... 
doi:10.1007/s10514-018-09826-z fatcat:67yqhwmgozccxni56rxmuapjgm

Advances and challenges in conversational recommender systems: A survey

Chongming Gao, Wenqiang Lei, Xiangnan He, Maarten de Rijke, Tat-Seng Chua
2021 AI Open  
We summarize the key challenges of developing CRSs in five directions: (1) Question-based user preference elicitation. (2) Multi-turn conversational recommendation strategies. (3) Dialogue understanding  ...  The recent rise of conversational recommender systems (CRSs) changes this situation fundamentally.  ...  Interactive Recommendation. Interactive recommendation models are mainly based on reinforcement learning.  ... 
doi:10.1016/j.aiopen.2021.06.002 fatcat:4r26fmsuvjcyla5wycb2ax62ha

Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Survey [article]

Jinjie Ni, Tom Young, Vlad Pandelea, Fuzhao Xue, Vinay Adiga, Erik Cambria
2021 arXiv   pre-print
, Neural Networks, CNN, RNN, Hierarchical Recurrent Encoder-Decoder, Memory Networks, Attention, Transformer, Pointer Net, CopyNet, Reinforcement Learning, GANs, Knowledge Graph, Survey, Review  ...  In this survey, we mainly focus on the deep learning-based dialogue systems.  ...  Almost all recent dialogue policy learning works are based on reinforcement learning methods.  ... 
arXiv:2105.04387v4 fatcat:stperoq73rgyja5b7zcfysjh5q

The Rapidly Changing Landscape of Conversational Agents [article]

Vinayak Mathur, Arpit Singh
2018 arXiv   pre-print
We look at statistical, neural, generative adversarial network based and reinforcement learning based approaches and how they evolved.  ...  Conversational agents have become ubiquitous, ranging from goal-oriented systems for helping with reservations to chit-chat models found in modern virtual assistants.  ...  The weights are themselves computed via a neural model learned from dialogue data.  ... 
arXiv:1803.08419v2 fatcat:5huy2e6tmbexlfoampcdy6zhw4

Advances and Challenges in Conversational Recommender Systems: A Survey [article]

Chongming Gao, Wenqiang Lei, Xiangnan He, Maarten de Rijke, Tat-Seng Chua
2021 arXiv   pre-print
We summarize the key challenges of developing CRSs in five directions: (1) Question-based user preference elicitation. (2) Multi-turn conversational recommendation strategies. (3) Dialogue understanding  ...  The recent rise of conversational recommender systems (CRSs) changes this situation fundamentally.  ...  The authors follow the idea of meta reinforcement learning [43] and use Q-Learning [121] to learn the recommendation policy.  ... 
arXiv:2101.09459v6 fatcat:j7djzhrv6fazpogmnj7r4e4f2y

Conversation Graph: Data Augmentation, Training, and Evaluation for Non-Deterministic Dialogue Management

Milan Gritta, Gerasimos Lampouras, Ignacio Iacobacci
2021 Transactions of the Association for Computational Linguistics  
We propose the Conversation Graph (ConvGraph), a graph-based representation of dialogues that can be exploited for data augmentation, multi- reference training and evaluation of non- deterministic agents  ...  ConvLab allows an agent to interact with the user simulator via dialogue acts, and supports reinforcement learning, supervised learning, and rule-based agents.  ...  Conclusions We have introduced the Conversation Graph for Dialogue Management, an approach that unifies conversations based on matching nodes (dialogue states).  ... 
doi:10.1162/tacl_a_00352 fatcat:morksq5zr5gnrcaqxidpv3erqq

Neural Approaches to Conversational AI [article]

Jianfeng Gao, Michel Galley, Lihong Li
2019 arXiv   pre-print
The present paper surveys neural approaches to conversational AI that have been developed in the last few years.  ...  We group conversational systems into three categories: (1) question answering agents, (2) task-oriented dialogue agents, and (3) chatbots.  ...  More information may be found in the DSTC website. 2 Dialogue Policy Learning In this section, we will focus on dialogue policy optimization based on reinforcement learning.  ... 
arXiv:1809.08267v3 fatcat:j57xlm4ogferdnrpfs4f2jporq
« Previous Showing results 1 — 15 out of 5,592 results