{"list":"other","total":160,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"1312.6114","title":"Auto-Encoding Variational Bayes","created":"2013-12-20","cited_by_count":4053},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"id":"1502.05477","title":"Trust Region Policy Optimization","created":"2015-02-19","cited_by_count":2580},{"id":"1602.01783","title":"Asynchronous Methods for Deep Reinforcement Learning","created":"2016-02-04","cited_by_count":2258},{"id":"1506.02438","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","created":"2015-06-08","cited_by_count":2026},{"id":"1509.06461","title":"Deep Reinforcement Learning with Double Q-learning","created":"2015-09-22","cited_by_count":1745},{"id":"1606.04671","title":"Progressive Neural Networks","created":"2016-06-15","cited_by_count":1361},{"id":"1911.08265","title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","created":"2019-11-19","cited_by_count":1353},{"id":"1702.05464","title":"Adversarial Discriminative Domain Adaptation","created":"2017-02-17","cited_by_count":1311},{"id":"1511.05952","title":"Prioritized Experience Replay","created":"2015-11-18","cited_by_count":1099},{"id":"1802.01561","title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures","created":"2018-02-05","cited_by_count":883},{"id":"1504.00702","title":"End-to-End Training of Deep Visuomotor Policies","created":"2015-04-02","cited_by_count":875},{"id":"1712.05884","title":"Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions","created":"2017-12-16","cited_by_count":804},{"id":"2009.06732","title":"Efficient Transformers: A Survey","created":"2020-09-14","cited_by_count":790},{"id":"1511.06581","title":"Dueling Network Architectures for Deep Reinforcement Learning","created":"2015-11-20","cited_by_count":785},{"id":"1805.12114","title":"Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models","created":"2018-05-30","cited_by_count":774},{"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":"1707.06887","title":"A Distributional Perspective on Reinforcement Learning","created":"2017-07-21","cited_by_count":765},{"id":"2002.00444","title":"Deep Reinforcement Learning for Autonomous Driving: A Survey","created":"2020-02-02","cited_by_count":721},{"id":"1810.02508","title":"MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations","created":"2018-10-05","cited_by_count":643},{"id":"1508.01211","title":"Listen, Attend and Spell","created":"2015-08-05","cited_by_count":543},{"id":"1611.02779","title":"RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning","created":"2016-11-09","cited_by_count":503},{"id":"1903.00374","title":"Model-Based Reinforcement Learning for Atari","created":"2019-03-01","cited_by_count":502},{"id":"1708.05866","title":"A Brief Survey of Deep Reinforcement Learning","created":"2017-08-19","cited_by_count":483},{"id":"1710.10044","title":"Distributional Reinforcement Learning with Quantile Regression","created":"2017-10-27","cited_by_count":474},{"id":"1507.06527","title":"Deep Recurrent Q-Learning for Partially Observable MDPs","created":"2015-07-23","cited_by_count":465},{"id":"1511.06295","title":"Policy Distillation","created":"2015-11-19","cited_by_count":440},{"id":"1909.05855","title":"Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Dataset","created":"2019-09-12","cited_by_count":434},{"id":"1611.05397","title":"Reinforcement Learning with Unsupervised Auxiliary Tasks","created":"2016-11-16","cited_by_count":404},{"id":"1802.03494","title":"AMC: AutoML for Model Compression and Acceleration on Mobile Devices","created":"2018-02-10","cited_by_count":378},{"id":"1611.05763","title":"Learning to reinforcement learn","created":"2016-11-17","cited_by_count":377},{"id":"1806.06923","title":"Implicit Quantile Networks for Distributional Reinforcement Learning","created":"2018-06-14","cited_by_count":369},{"id":"1609.05143","title":"Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning","created":"2016-09-16","cited_by_count":366},{"id":"1701.07274","title":"Deep Reinforcement Learning: An Overview","created":"2017-01-25","cited_by_count":333},{"id":"1606.01541","title":"Deep Reinforcement Learning for Dialogue Generation","created":"2016-06-05","cited_by_count":288},{"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":"1606.02647","title":"Safe and Efficient Off-Policy Reinforcement Learning","created":"2016-06-08","cited_by_count":264},{"id":"1704.02532","title":"Deep Reinforcement Learning framework for Autonomous Driving","created":"2017-04-08","cited_by_count":225},{"id":"1506.00019","title":"A Critical Review of Recurrent Neural Networks for Sequence Learning","created":"2015-05-29","cited_by_count":224},{"id":"1811.00405","title":"DialogueRNN: An Attentive RNN for Emotion Detection in Conversations","created":"2018-11-01","cited_by_count":218},{"id":"1708.07524","title":"Supervised Speech Separation Based on Deep Learning: An Overview","created":"2017-08-24","cited_by_count":216},{"id":"1901.06032","title":"A Survey of the Recent Architectures of Deep Convolutional Neural Networks","created":"2019-01-17","cited_by_count":213},{"id":"1909.06317","title":"A Comparative Study on Transformer vs RNN in Speech Applications","created":"2019-09-13","cited_by_count":211},{"id":"1811.12560","title":"An Introduction to Deep Reinforcement Learning","created":"2018-11-30","cited_by_count":206},{"id":"1611.01224","title":"Sample Efficient Actor-Critic with Experience Replay","created":"2016-11-03","cited_by_count":188},{"id":"1810.05587","title":"A Survey and Critique of Multiagent Deep Reinforcement Learning","created":"2018-10-12","cited_by_count":177},{"id":"1704.06440","title":"Equivalence Between Policy Gradients and Soft Q-Learning","created":"2017-04-21","cited_by_count":173},{"id":"1806.07857","title":"RUDDER: Return Decomposition for Delayed Rewards","created":"2018-06-20","cited_by_count":173},{"id":"1807.01675","title":"Sample-Efficient Reinforcement Learning with Stochastic Ensemble Value Expansion","created":"2018-07-04","cited_by_count":168},{"id":"1704.01074","title":"Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memory","created":"2017-04-04","cited_by_count":167},{"id":"1810.07862","title":"Applications of Deep Reinforcement Learning in Communications and Networking: A Survey","created":"2018-10-18","cited_by_count":167},{"id":"1809.08267","title":"Neural Approaches to Conversational AI","created":"2018-09-21","cited_by_count":165},{"id":"2006.06873","title":"FastPitch: Parallel Text-to-speech with Pitch Prediction","created":"2020-06-11","cited_by_count":151},{"id":"1812.11794","title":"Deep Reinforcement Learning for Multi-Agent Systems: A Review of Challenges, Solutions and Applications","created":"2018-12-31","cited_by_count":127},{"id":"1905.02947","title":"Emotion Recognition in Conversation: Research Challenges, Datasets, and Recent Advances","created":"2019-05-08","cited_by_count":119},{"id":"1705.10843","title":"Objective-Reinforced Generative Adversarial Networks (ORGAN) for Sequence Generation Models","created":"2017-05-30","cited_by_count":117},{"id":"1707.03497","title":"Value Prediction Network","created":"2017-07-11","cited_by_count":117},{"id":"1701.06547","title":"Adversarial Learning for Neural Dialogue Generation","created":"2017-01-23","cited_by_count":103},{"id":"1706.06551","title":"Grounded Language Learning in a Simulated 3D World","created":"2017-06-20","cited_by_count":100},{"id":"2005.00935","title":"Deep Reinforcement Learning for Intelligent Transportation Systems: A Survey","created":"2020-05-02","cited_by_count":98},{"id":"1912.11684","title":"Look, Listen, and Act: Towards Audio-Visual Embodied Navigation","created":"2019-12-25","cited_by_count":96},{"id":"1905.00078","title":"Deep Learning for Audio Signal Processing","created":"2019-04-30","cited_by_count":92},{"id":"1702.08360","title":"Neural Map: Structured Memory for Deep Reinforcement Learning","created":"2017-02-27","cited_by_count":90},{"id":"1801.01078","title":"Recent Advances in Recurrent Neural Networks","created":"2017-12-29","cited_by_count":89},{"id":"1704.00057","title":"Frames: A Corpus for Adding Memory to Goal-Oriented Dialogue Systems","created":"2017-03-31","cited_by_count":85},{"id":"1704.00784","title":"Online and Linear-Time Attention by Enforcing Monotonic Alignments","created":"2017-04-03","cited_by_count":85},{"id":"1703.06585","title":"Learning Cooperative Visual Dialog Agents with Deep Reinforcement Learning","created":"2017-03-20","cited_by_count":71},{"id":"1901.10623","title":"End-to-End Knowledge-Routed Relational Dialogue System for Automatic Diagnosis","created":"2019-01-30","cited_by_count":70},{"id":"1605.09128","title":"Control of Memory, Active Perception, and Action in Minecraft","created":"2016-05-30","cited_by_count":61},{"id":"1910.10279","title":"WHAMR!: Noisy and Reverberant Single-Channel Speech Separation","created":"2019-10-22","cited_by_count":61},{"id":"2005.08575","title":"Audio ALBERT: A Lite BERT for Self-supervised Learning of Audio Representation","created":"2020-05-18","cited_by_count":59},{"id":"1611.09827","title":"Learning Features of Music from Scratch","created":"2016-11-29","cited_by_count":58},{"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":"2001.01102","title":"MushroomRL: Simplifying Reinforcement Learning Research","created":"2020-01-04","cited_by_count":50},{"id":"2006.05779","title":"Self-Supervised Reinforcement Learning for Recommender Systems","created":"2020-06-10","cited_by_count":49},{"id":"1611.06256","title":"Reinforcement Learning through Asynchronous Advantage Actor-Critic on a GPU","created":"2016-11-18","cited_by_count":48},{"id":"1904.13377","title":"Very Deep Self-Attention Networks for End-to-End Speech Recognition","created":"2019-04-30","cited_by_count":46},{"id":"1704.03084","title":"Composite Task-Completion Dialogue Policy Learning via Hierarchical Deep Reinforcement Learning","created":"2017-04-10","cited_by_count":44},{"id":"1805.11593","title":"Observe and Look Further: Achieving Consistent Performance on Atari","created":"2018-05-29","cited_by_count":44},{"id":"1802.00924","title":"Multimodal Sentiment Analysis with Word-Level Fusion and Reinforcement Learning","created":"2018-02-03","cited_by_count":43},{"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":"1709.02349","title":"A Deep Reinforcement Learning Chatbot","created":"2017-09-07","cited_by_count":36},{"id":"1610.03022","title":"Very Deep Convolutional Networks for End-to-End Speech Recognition","created":"2016-10-10","cited_by_count":34},{"id":"1512.05742","title":"A Survey of Available Corpora for Building Data-Driven Dialogue Systems","created":"2015-12-17","cited_by_count":33},{"id":"1705.04862","title":"Efficient Parallel Methods for Deep Reinforcement Learning","created":"2017-05-13","cited_by_count":32},{"id":"1606.04695","title":"Strategic Attentive Writer for Learning Macro-Actions","created":"2016-06-15","cited_by_count":30},{"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":"2001.00378","title":"Deep Representation Learning in Speech Processing: Challenges, Recent Advances, and Future Trends","created":"2020-01-02","cited_by_count":28},{"id":"1512.01693","title":"Deep Attention Recurrent Q-Network","created":"2015-12-05","cited_by_count":27},{"id":"1704.04222","title":"Learning Latent Representations for Speech Generation and Transformation","created":"2017-04-13","cited_by_count":27},{"id":"1909.07547","title":"Hierarchical Reinforcement Learning for Open-Domain Dialog","created":"2019-09-17","cited_by_count":27},{"id":"1611.01626","title":"Combining policy gradient and Q-learning","created":"2016-11-05","cited_by_count":24},{"id":"1603.09725","title":"Audio-Visual Speaker Diarization Based on Spatiotemporal Bayesian Fusion","created":"2016-03-31","cited_by_count":23},{"id":"1802.01433","title":"Interactive Grounded Language Acquisition and Generalization in a 2D World","created":"2018-01-31","cited_by_count":21},{"id":"1711.10712","title":"End-to-End Optimization of Task-Oriented Dialogue Model with Deep Reinforcement Learning","created":"2017-11-29","cited_by_count":19}],"next_cursor":"100"}