{"list":"other","total":63,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1910.13461","title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension","created":"2019-10-29","cited_by_count":5893},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"1509.02971","title":"Continuous control with deep reinforcement learning","created":"2015-09-09","cited_by_count":3407},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"1910.03771","title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","created":"2019-10-09","cited_by_count":2218},{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150},{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920},{"id":"2112.09332","title":"WebGPT: Browser-assisted question-answering with human feedback","created":"2021-12-17","cited_by_count":1745},{"id":"1606.03476","title":"Generative Adversarial Imitation Learning","created":"2016-06-10","cited_by_count":1597},{"id":"1611.00712","title":"The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables","created":"2016-11-02","cited_by_count":1148},{"id":"1707.01495","title":"Hindsight Experience Replay","created":"2017-07-05","cited_by_count":1136},{"id":"2106.06860","title":"A Minimalist Approach to Offline Reinforcement Learning","created":"2021-06-12","cited_by_count":899},{"id":"1810.00278","title":"MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling","created":"2018-09-29","cited_by_count":766},{"id":"1710.11248","title":"Learning Robust Rewards with Adversarial Inverse Reinforcement Learning","created":"2017-10-30","cited_by_count":490},{"id":"2003.04807","title":"Efficient Intent Detection with Dual Sentence Encoders","created":"2020-03-10","cited_by_count":433},{"id":"2005.00796","title":"A Simple Language Model for Task-Oriented Dialogue","created":"2020-05-02","cited_by_count":332},{"id":"2203.11147","title":"Teaching language models to support answers with verified quotes","created":"2022-03-21","cited_by_count":292},{"id":"1907.00456","title":"Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog","created":"2019-06-30","cited_by_count":284},{"id":"2006.15134","title":"Critic Regularized Regression","created":"2020-06-26","cited_by_count":275},{"id":"1904.06387","title":"Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observations","created":"2019-04-12","cited_by_count":260},{"id":"1604.04562","title":"A Network-based End-to-End Trainable Task-oriented Dialogue System","created":"2016-04-15","cited_by_count":252},{"id":"1905.08743","title":"Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems","created":"2019-05-21","cited_by_count":216},{"id":"1611.03852","title":"A Connection between Generative Adversarial Networks, Inverse Reinforcement Learning, and Energy-Based Models","created":"2016-11-11","cited_by_count":168},{"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":"2206.11871","title":"Offline RL for Natural Language Generation with Implicit Language Q Learning","created":"2022-06-05","cited_by_count":138},{"id":"1508.01745","title":"Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems","created":"2015-08-07","cited_by_count":134},{"id":"2012.03539","title":"UBAR: Towards Fully End-to-End Task-Oriented Dialog Systems with GPT-2","created":"2020-12-07","cited_by_count":111},{"id":"2009.12005","title":"MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systems","created":"2020-09-25","cited_by_count":103},{"id":"2111.14592","title":"GALAXY: A Generative Pre-trained Model for Task-Oriented Dialog with Semi-Supervised Learning and Explicit Policy Injection","created":"2021-11-29","cited_by_count":102},{"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":"2009.06799","title":"The Importance of Pessimism in Fixed-Dataset Policy Optimization","created":"2020-09-15","cited_by_count":99},{"id":"2010.05848","title":"Human-centric Dialog Training via Offline Reinforcement Learning","created":"2020-10-12","cited_by_count":93},{"id":"1910.03544","title":"Find or Classify? Dual Strategy for Slot-Value Predictions on Multi-Domain Dialog State Tracking","created":"2019-10-08","cited_by_count":75},{"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":"2002.04793","title":"ConvLab-2: An Open-Source Toolkit for Building, Evaluating, and Diagnosing Dialogue Systems","created":"2020-02-12","cited_by_count":52},{"id":"2010.10604","title":"Bayesian Attention Modules","created":"2020-10-20","cited_by_count":51},{"id":"2106.01494","title":"Knowing More About Questions Can Help: Improving Calibration in Question Answering","created":"2021-06-02","cited_by_count":47},{"id":"1704.03084","title":"Composite Task-Completion Dialogue Policy Learning via Hierarchical Deep Reinforcement Learning","created":"2017-04-10","cited_by_count":44},{"id":"1907.10016","title":"Structured Fusion Networks for Dialog","created":"2019-07-23","cited_by_count":40},{"id":"2105.13345","title":"Adversarial Intrinsic Motivation for Reinforcement Learning","created":"2021-05-27","cited_by_count":40},{"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":"2204.08426","title":"CHAI: A CHatbot AI for Task-Oriented Dialogue with Offline Reinforcement Learning","created":"2022-04-18","cited_by_count":34},{"id":"2105.14150","title":"Annotation Inconsistency and Entity Bias in MultiWOZ","created":"2021-05-29","cited_by_count":30},{"id":"2202.13675","title":"A Survey on Recent Advances and Challenges in Reinforcement Learning Methods for Task-Oriented Dialogue Policy Learning","created":"2022-02-28","cited_by_count":30},{"id":"2109.04408","title":"Learning with Different Amounts of Annotation: From Zero to Many Labels","created":"2021-09-09","cited_by_count":28},{"id":"2103.04181","title":"Contextual Dropout: An Efficient Sample-Dependent Dropout Module","created":"2021-03-06","cited_by_count":26},{"id":"1910.03756","title":"Alternating Recurrent Dialog Model with Large-scale Pre-trained Language Models","created":"2019-10-09","cited_by_count":25},{"id":"1902.00528","title":"Competitive Experience Replay","created":"2019-02-01","cited_by_count":23},{"id":"2205.04980","title":"ALLSH: Active Learning Guided by Local Sensitivity and Hardness","created":"2022-05-10","cited_by_count":23},{"id":"2204.10198","title":"Context-Aware Language Modeling for Goal-Oriented Dialogue Systems","created":"2022-04-18","cited_by_count":22},{"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":"2206.07166","title":"Regularizing a Model-based Policy Stationary Distribution to Stabilize Offline Reinforcement Learning","created":"2022-06-14","cited_by_count":14},{"id":"2210.05922","title":"A Unified Framework for Alternating Offline Model Training and Policy Learning","created":"2022-10-12","cited_by_count":14},{"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":"1905.01413","title":"ARSM: Augment-REINFORCE-Swap-Merge Estimator for Gradient Backpropagation Through Categorical Variables","created":"2019-05-04","cited_by_count":10},{"id":"1808.07645","title":"Playing 20 Question Game with Policy-Based Reinforcement Learning","created":"2018-08-23","cited_by_count":9},{"id":"2004.03267","title":"Guided Dialog Policy Learning without Adversarial Learning in the Loop","created":"2020-04-07","cited_by_count":7},{"id":"2211.00915","title":"Passage-Mask: A Learnable Regularization Strategy for Retriever-Reader Models","created":"2022-11-02","cited_by_count":6}],"next_cursor":null}