{"list":"other","total":67,"rows":[{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"id":"1606.03476","title":"Generative Adversarial Imitation Learning","created":"2016-06-10","cited_by_count":1597},{"id":"1609.05140","title":"The Option-Critic Architecture","created":"2016-09-16","cited_by_count":448},{"id":"1905.08743","title":"Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems","created":"2019-05-21","cited_by_count":216},{"id":"1706.05125","title":"Deal or No Deal? End-to-End Learning for Negotiation Dialogues","created":"2017-06-16","cited_by_count":209},{"id":"1506.05869","title":"A Neural Conversational Model","created":"2015-06-19","cited_by_count":196},{"id":"1902.10909","title":"BERT for Joint Intent Classification and Slot Filling","created":"2019-02-28","cited_by_count":196},{"id":"1809.08267","title":"Neural Approaches to Conversational AI","created":"2018-09-21","cited_by_count":165},{"id":"1711.01731","title":"A Survey on Dialogue Systems: Recent Advances and New Frontiers","created":"2017-11-06","cited_by_count":162},{"id":"1606.03777","title":"Neural Belief Tracker: Data-Driven Dialogue State Tracking","created":"2016-06-12","cited_by_count":143},{"id":"1503.02364","title":"Neural Responding Machine for Short-Text Conversation","created":"2015-03-09","cited_by_count":124},{"id":"1703.00956","title":"A Laplacian Framework for Option Discovery in Reinforcement Learning","created":"2017-03-02","cited_by_count":110},{"id":"1911.10484","title":"Task-Oriented Dialog Systems that Consider Multiple Appropriate Responses under the Same Context","created":"2019-11-24","cited_by_count":99},{"id":"2003.07490","title":"Recent Advances and Challenges in Task-oriented Dialog System","created":"2020-03-17","cited_by_count":78},{"id":"1908.01946","title":"Dialog State Tracking: A Neural Reading Comprehension Approach","created":"2019-08-06","cited_by_count":62},{"id":"1612.05688","title":"A User Simulator for Task-Completion Dialogues","created":"2016-12-17","cited_by_count":57},{"id":"1902.08858","title":"Rethinking Action Spaces for Reinforcement Learning in End-to-end Dialog Agents with Latent Variable Models","created":"2019-02-23","cited_by_count":53},{"id":"1704.03084","title":"Composite Task-Completion Dialogue Policy Learning via Hierarchical Deep Reinforcement Learning","created":"2017-04-10","cited_by_count":44},{"id":"1905.12866","title":"Semantically Conditioned Dialog Response Generation via Hierarchical Disentangled Self-Attention","created":"2019-05-30","cited_by_count":44},{"id":"1607.00070","title":"A Sequence-to-Sequence Model for User Simulation in Spoken Dialogue Systems","created":"2016-06-30","cited_by_count":39},{"id":"1908.10719","title":"Guided Dialog Policy Learning: Reward Estimation for Multi-Domain Task-Oriented Dialog","created":"2019-08-28","cited_by_count":37},{"id":"1711.05715","title":"BBQ-Networks: Efficient Exploration in Deep Reinforcement Learning for Task-Oriented Dialogue Systems","created":"2017-11-15","cited_by_count":30},{"id":"1606.02560","title":"Towards End-to-End Learning for Dialog State Tracking and Management using Deep Reinforcement Learning","created":"2016-06-08","cited_by_count":29},{"id":"1605.07669","title":"On-line Active Reward Learning for Policy Optimisation in Spoken Dialogue Systems","created":"2016-05-24","cited_by_count":28},{"id":"2006.06814","title":"Modelling Hierarchical Structure between Dialogue Policy and Natural Language Generator with Option Framework for Task-oriented Dialogue System","created":"2020-06-11","cited_by_count":28},{"id":"1709.06136","title":"Iterative Policy Learning in End-to-End Trainable Task-Oriented Neural Dialog Models","created":"2017-09-18","cited_by_count":26},{"id":"2004.12363","title":"Multi-Domain Dialogue Acts and Response Co-Generation","created":"2020-04-26","cited_by_count":26},{"id":"1905.05644","title":"Meta-Learning for Low-resource Natural Language Generation in Task-oriented Dialogue Systems","created":"2019-05-14","cited_by_count":25},{"id":"2004.03809","title":"Multi-Agent Task-Oriented Dialog Policy Learning with Role-Aware Reward Decomposition","created":"2020-04-08","cited_by_count":23},{"id":"1801.06176","title":"Deep Dyna-Q: Integrating Planning for Task-Completion Dialogue Policy Learning","created":"2018-01-18","cited_by_count":21},{"id":"2005.07362","title":"Is Your Goal-Oriented Dialog Model Performing Really Well? Empirical Analysis of System-wise Evaluation","created":"2020-05-15","cited_by_count":19},{"id":"1702.07463","title":"Sequence Modeling via Segmentations","created":"2017-02-24","cited_by_count":18},{"id":"1707.00130","title":"Sample-efficient Actor-Critic Reinforcement Learning with Supervised Data for Dialogue Management","created":"2017-07-01","cited_by_count":18},{"id":"1805.11762","title":"Adversarial Learning of Task-Oriented Neural Dialog Models","created":"2018-05-30","cited_by_count":17},{"id":"2004.09731","title":"Learning Goal-oriented Dialogue Policy with Opposite Agent Awareness","created":"2020-04-21","cited_by_count":16},{"id":"1802.03753","title":"Sample Efficient Deep Reinforcement Learning for Dialogue Systems with Large Action Spaces","created":"2018-02-11","cited_by_count":15},{"id":"1606.03152","title":"Policy Networks with Two-Stage Training for Dialogue Systems","created":"2016-06-10","cited_by_count":14},{"id":"1701.04024","title":"A Copy-Augmented Sequence-to-Sequence Architecture Gives Good Performance on Task-Oriented Dialogue","created":"2017-01-15","cited_by_count":14},{"id":"1906.00499","title":"Budgeted Policy Learning for Task-Oriented Dialogue Systems","created":"2019-06-02","cited_by_count":13},{"id":"1606.02689","title":"Continuously Learning Neural Dialogue Management","created":"2016-06-08","cited_by_count":12},{"id":"1811.07550","title":"Switch-based Active Deep Dyna-Q: Efficient Adaptive Planning for Task-Completion Dialogue Policy Learning","created":"2018-11-19","cited_by_count":12},{"id":"1802.00500","title":"Goal-Oriented Chatbot Dialog Management Bootstrapping with Transfer Learning","created":"2018-02-01","cited_by_count":11},{"id":"1803.03232","title":"Feudal Reinforcement Learning for Dialogue Management in Large Domains","created":"2018-03-08","cited_by_count":11},{"id":"1808.09442","title":"Discriminative Deep Dyna-Q: Robust Planning for Dialogue Policy Learning","created":"2018-08-28","cited_by_count":11},{"id":"1710.11277","title":"Adversarial Advantage Actor-Critic Model for Task-Completion Dialogue Policy Learning","created":"2017-10-31","cited_by_count":10},{"id":"2004.11054","title":"Learning Dialog Policies from Weak Demonstrations","created":"2020-04-23","cited_by_count":10},{"id":"1508.03391","title":"Reward Shaping with Recurrent Neural Networks for Speeding up On-Line Policy Learning in Spoken Dialogue Systems","created":"2015-08-14","cited_by_count":9},{"id":"1804.07855","title":"Subgoal Discovery for Hierarchical Dialogue Policy Learning","created":"2018-04-20","cited_by_count":9},{"id":"1907.05507","title":"Collaborative Multi-Agent Dialogue Model Training Via Reinforcement Learning","created":"2019-07-11","cited_by_count":9},{"id":"1508.03386","title":"Learning from Real Users: Rating Dialogue Success with Neural Networks for Reinforcement Learning in Spoken Dialogue Systems","created":"2015-08-13","cited_by_count":8},{"id":"1706.06210","title":"Sub-domain Modelling for Dialogue Management with Hierarchical Reinforcement Learning","created":"2017-06-19","cited_by_count":8},{"id":"1805.03257","title":"Multimodal Hierarchical Reinforcement Learning Policy for Task-Oriented Visual Dialog","created":"2018-05-08","cited_by_count":8},{"id":"1808.06497","title":"Goal-oriented Dialogue Policy Learning from Failures","created":"2018-08-20","cited_by_count":8},{"id":"2005.02233","title":"A Survey on Dialog Management: Recent Advances and Challenges","created":"2020-05-05","cited_by_count":8},{"id":"2005.04379","title":"Semi-Supervised Dialogue Policy Learning via Stochastic Reward Estimation","created":"2020-05-09","cited_by_count":8},{"id":"2106.02317","title":"Retrieve & Memorize: Dialog Policy Learning with Multi-Action Memory","created":"2021-06-04","cited_by_count":8},{"id":"2004.03267","title":"Guided Dialog Policy Learning without Adversarial Learning in the Loop","created":"2020-04-07","cited_by_count":7},{"id":"1710.00164","title":"Speaker Role Contextual Modeling for Language Understanding and Dialogue Policy Learning","created":"2017-09-30","cited_by_count":6},{"id":"2005.03299","title":"Adaptive Dialog Policy Learning with Hindsight and User Modeling","created":"2020-05-07","cited_by_count":5},{"id":"1908.11546","title":"Modeling Multi-Action Policy for Task-Oriented Dialogues","created":"2019-08-30","cited_by_count":4},{"id":"1611.08675","title":"Deep Reinforcement Learning for Multi-Domain Dialogue Systems","created":"2016-11-26","cited_by_count":3},{"id":"2004.08114","title":"Show Us the Way: Learning to Manage Dialog from Demonstrations","created":"2020-04-17","cited_by_count":3},{"id":"2006.02588","title":"Meta Dialogue Policy Learning","created":"2020-06-03","cited_by_count":3},{"id":"1804.07691","title":"Cross-domain Dialogue Policy Transfer via Simultaneous Speech-act and Slot Alignment","created":"2018-04-20","cited_by_count":1},{"id":"2004.10698","title":"AutoEG: Automated Experience Grafting for Off-Policy Deep Reinforcement Learning","created":"2020-04-22","cited_by_count":1}],"next_cursor":null}