{"list":"other","total":55,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"2010.03768","title":"ALFWorld: Aligning Text and Embodied Environments for Interactive Learning","created":"2020-10-08","cited_by_count":1205},{"id":"1705.05363","title":"Curiosity-driven Exploration by Self-supervised Prediction","created":"2017-05-15","cited_by_count":1194},{"id":"1511.07289","title":"Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)","created":"2015-11-23","cited_by_count":1070},{"id":"1711.07280","title":"Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments","created":"2017-11-20","cited_by_count":1027},{"id":"1810.12894","title":"Exploration by Random Network Distillation","created":"2018-10-30","cited_by_count":993},{"id":"1802.01561","title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures","created":"2018-02-05","cited_by_count":883},{"id":"2108.13264","title":"Deep Reinforcement Learning at the Edge of the Statistical Precipice","created":"2021-08-30","cited_by_count":807},{"id":"1912.01734","title":"ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks","created":"2019-12-03","cited_by_count":783},{"id":"1606.01868","title":"Unifying Count-Based Exploration and Intrinsic Motivation","created":"2016-06-06","cited_by_count":639},{"id":"1806.02724","title":"Speaker-Follower Models for Vision-and-Language Navigation","created":"2018-06-07","cited_by_count":340},{"id":"1806.11532","title":"TextWorld: A Learning Environment for Text-based Games","created":"2018-06-29","cited_by_count":310},{"id":"1611.04717","title":"#Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning","created":"2016-11-15","cited_by_count":309},{"id":"1703.01310","title":"Count-Based Exploration with Neural Density Models","created":"2017-03-03","cited_by_count":257},{"id":"1810.08272","title":"BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learning","created":"2018-10-18","cited_by_count":244},{"id":"1811.12354","title":"Touchdown: Natural Language Navigation and Spatial Reasoning in Visual Street Environments","created":"2018-11-29","cited_by_count":239},{"id":"1707.05300","title":"Reverse Curriculum Generation for Reinforcement Learning","created":"2017-07-17","cited_by_count":198},{"id":"2006.13760","title":"The NetHack Learning Environment","created":"2020-06-24","cited_by_count":198},{"id":"1507.00814","title":"Incentivizing Exploration In Reinforcement Learning With Deep Predictive Models","created":"2015-07-03","cited_by_count":154},{"id":"1906.03926","title":"A Survey of Reinforcement Learning Informed by Natural Language","created":"2019-06-10","cited_by_count":154},{"id":"2003.04664","title":"Automatic Curriculum Learning For Deep RL: A Short Survey","created":"2020-03-10","cited_by_count":150},{"id":"1906.07343","title":"Language as an Abstraction for Hierarchical Deep Reinforcement Learning","created":"2019-06-18","cited_by_count":138},{"id":"2002.12292","title":"RIDE: Rewarding Impact-Driven Exploration for Procedurally-Generated Environments","created":"2020-02-27","cited_by_count":135},{"id":"1903.03094","title":"Learning to Speak and Act in a Fantasy Text Adventure Game","created":"2019-03-07","cited_by_count":122},{"id":"1910.07224","title":"Teacher algorithms for curriculum learning of Deep RL in continuously parameterized environments","created":"2019-10-16","cited_by_count":119},{"id":"1903.02020","title":"Using Natural Language for Reward Shaping in Reinforcement Learning","created":"2019-03-05","cited_by_count":114},{"id":"1807.11622","title":"Count-Based Exploration with the Successor Representation","created":"2018-07-31","cited_by_count":112},{"id":"2109.13202","title":"MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research","created":"2021-09-27","cited_by_count":97},{"id":"2006.12122","title":"Learning with AMIGo: Adversarially Motivated Intrinsic Goals","created":"2020-06-22","cited_by_count":88},{"id":"2012.09830","title":"Autotelic Agents with Intrinsically Motivated Goal-Conditioned Reinforcement Learning: a Short Survey","created":"2020-12-17","cited_by_count":85},{"id":"1703.01732","title":"Surprise-Based Intrinsic Motivation for Deep Reinforcement Learning","created":"2017-03-06","cited_by_count":83},{"id":"1708.02190","title":"Intrinsically Motivated Goal Exploration Processes with Automatic Curriculum Learning","created":"2017-08-07","cited_by_count":83},{"id":"1704.08795","title":"Mapping Instructions and Visual Observations to Actions with Reinforcement Learning","created":"2017-04-28","cited_by_count":81},{"id":"1806.01946","title":"Learning to Understand Goal Specifications by Modelling Reward","created":"2018-06-05","cited_by_count":80},{"id":"1711.00482","title":"Learning with Latent Language","created":"2017-11-01","cited_by_count":75},{"id":"2002.09253","title":"Language as a Cognitive Tool to Imagine Goals in Curiosity-Driven Exploration","created":"2020-02-21","cited_by_count":68},{"id":"1902.07742","title":"From Language to Goals: Inverse Reinforcement Learning for Vision-Based Instruction Following","created":"2019-02-20","cited_by_count":67},{"id":"1812.01628","title":"Playing Text-Adventure Games with Graph-Based Deep Reinforcement Learning","created":"2018-12-04","cited_by_count":53},{"id":"1706.08090","title":"Count-Based Exploration in Feature Space for Reinforcement Learning","created":"2017-06-25","cited_by_count":49},{"id":"2101.07393","title":"Grounding Language to Entities and Dynamics for Generalization in Reinforcement Learning","created":"2021-01-19","cited_by_count":45},{"id":"1910.09664","title":"Learning to Map Natural Language Instructions to Physical Quadcopter Control using Simulated Flight","created":"2019-10-21","cited_by_count":43},{"id":"2103.05825","title":"ELLA: Exploration through Learned Language Abstraction","created":"2021-03-10","cited_by_count":42},{"id":"1910.03552","title":"TorchBeast: A PyTorch Platform for Distributed RL","created":"2019-10-08","cited_by_count":41},{"id":"1401.5390","title":"Learning to Win by Reading Manuals in a Monte-Carlo Framework","created":"2014-01-18","cited_by_count":39},{"id":"2011.00517","title":"Ask Your Humans: Using Human Instructions to Improve Generalization in Reinforcement Learning","created":"2020-11-01","cited_by_count":32},{"id":"1906.00744","title":"Hierarchical Decision Making by Generating and Following Natural Language Instructions","created":"2019-06-03","cited_by_count":30},{"id":"2007.15543","title":"PixL2R: Guiding Reinforcement Learning Using Natural Language by Mapping Pixels to Rewards","created":"2020-07-30","cited_by_count":30},{"id":"1909.12892","title":"Automated curricula through setter-solver interactions","created":"2019-09-27","cited_by_count":26},{"id":"1911.00497","title":"A Narration-based Reward Shaping Approach using Grounded Natural Language Commands","created":"2019-10-31","cited_by_count":16},{"id":"2006.07043","title":"Language-Conditioned Goal Generation: a New Approach to Language Grounding for RL","created":"2020-06-12","cited_by_count":12},{"id":"1707.08616","title":"Guiding Reinforcement Learning Exploration Using Natural Language","created":"2017-07-26","cited_by_count":10},{"id":"1910.02789","title":"Language is Power: Representing States Using Natural Language in Reinforcement Learning","created":"2019-10-02","cited_by_count":7},{"id":"2110.04649","title":"Interactive Hierarchical Guidance using Language","created":"2021-10-09","cited_by_count":5},{"id":"2104.01506","title":"Influencing Reinforcement Learning through Natural Language Guidance","created":"2021-04-04","cited_by_count":4}],"next_cursor":null}