{"list":"other","total":53,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1301.3781","title":"Efficient Estimation of Word Representations in Vector Space","created":"2013-01-16","cited_by_count":4375},{"id":"2307.15818","title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","created":"2023-07-28","cited_by_count":3080},{"id":"1709.07871","title":"FiLM: Visual Reasoning with a General Conditioning Layer","created":"2017-09-22","cited_by_count":2333},{"id":"2006.04779","title":"Conservative Q-Learning for Offline Reinforcement Learning","created":"2020-06-08","cited_by_count":1809},{"id":"2110.06169","title":"Offline Reinforcement Learning with Implicit Q-Learning","created":"2021-10-12","cited_by_count":1293},{"id":"1812.02900","title":"Off-Policy Deep Reinforcement Learning without Exploration","created":"2018-12-07","cited_by_count":1241},{"id":"1707.01495","title":"Hindsight Experience Replay","created":"2017-07-05","cited_by_count":1136},{"id":"1912.01734","title":"ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks","created":"2019-12-03","cited_by_count":783},{"id":"1707.06887","title":"A Distributional Perspective on Reinforcement Learning","created":"2017-07-21","cited_by_count":765},{"id":"2203.12601","title":"R3M: A Universal Visual Representation for Robot Manipulation","created":"2022-03-23","cited_by_count":694},{"id":"2202.02005","title":"BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning","created":"2022-02-04","cited_by_count":523},{"id":"2306.13831","title":"Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Tasks","created":"2023-06-24","cited_by_count":327},{"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":"2202.01771","title":"Pre-Trained Language Models for Interactive Decision-Making","created":"2022-02-03","cited_by_count":221},{"id":"1502.02259","title":"Contextual Markov Decision Processes","created":"2015-02-08","cited_by_count":220},{"id":"2005.07648","title":"Language Conditioned Imitation Learning over Unstructured Data","created":"2020-05-15","cited_by_count":209},{"id":"1611.01796","title":"Modular Multitask Reinforcement Learning with Policy Sketches","created":"2016-11-06","cited_by_count":203},{"id":"2302.02662","title":"Grounding Large Language Models in Interactive Environments with Online Reinforcement Learning","created":"2023-02-06","cited_by_count":195},{"id":"1906.05838","title":"Goal-conditioned Imitation Learning","created":"2019-06-13","cited_by_count":162},{"id":"1906.03926","title":"A Survey of Reinforcement Learning Informed by Natural Language","created":"2019-06-10","cited_by_count":154},{"id":"2307.11949","title":"HIQL: Offline Goal-Conditioned RL with Latent States as Actions","created":"2023-07-22","cited_by_count":141},{"id":"2204.06252","title":"What Matters in Language Conditioned Robotic Imitation Learning over Unstructured Data","created":"2022-04-13","cited_by_count":138},{"id":"2010.12083","title":"Language-Conditioned Imitation Learning for Robot Manipulation Tasks","created":"2020-10-22","cited_by_count":136},{"id":"2107.00541","title":"Goal-Conditioned Reinforcement Learning with Imagined Subgoals","created":"2021-07-01","cited_by_count":134},{"id":"2109.01115","title":"Learning Language-Conditioned Robot Behavior from Offline Data and Crowd-Sourced Annotation","created":"2021-09-02","cited_by_count":118},{"id":"1903.02020","title":"Using Natural Language for Reward Shaping in Reinforcement Learning","created":"2019-03-05","cited_by_count":114},{"id":"1706.06551","title":"Grounded Language Learning in a Simulated 3D World","created":"2017-06-20","cited_by_count":100},{"id":"2309.10228","title":"Drive as You Speak: Enabling Human-Like Interaction with Large Language Models in Autonomous Vehicles","created":"2023-09-19","cited_by_count":100},{"id":"2202.04478","title":"Rethinking Goal-conditioned Supervised Learning and Its Connection to Offline RL","created":"2022-02-09","cited_by_count":89},{"id":"1704.08795","title":"Mapping Instructions and Visual Observations to Actions with Reinforcement Learning","created":"2017-04-28","cited_by_count":81},{"id":"2211.15144","title":"Offline Q-Learning on Diverse Multi-Task Data Both Scales And Generalizes","created":"2022-11-28","cited_by_count":73},{"id":"1706.07230","title":"Gated-Attention Architectures for Task-Oriented Language Grounding","created":"2017-06-22","cited_by_count":72},{"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":"2109.08128","title":"Conservative Data Sharing for Multi-Task Offline Reinforcement Learning","created":"2021-09-16","cited_by_count":64},{"id":"2006.11485","title":"Generating Adjacency-Constrained Subgoals in Hierarchical Reinforcement Learning","created":"2020-06-20","cited_by_count":58},{"id":"2002.11708","title":"Generalized Hindsight for Reinforcement Learning","created":"2020-02-26","cited_by_count":51},{"id":"2205.11790","title":"Hierarchical Planning Through Goal-Conditioned Offline Reinforcement Learning","created":"2022-05-24","cited_by_count":50},{"id":"1804.10556","title":"Convergence and Concentration of Empirical Measures under Wasserstein Distance in Unbounded Functional Spaces","created":"2018-04-27","cited_by_count":41},{"id":"1811.07882","title":"Guiding Policies with Language via Meta-Learning","created":"2018-11-19","cited_by_count":35},{"id":"2307.00117","title":"Goal Representations for Instruction Following: A Semi-Supervised Language Interface to Control","created":"2023-06-30","cited_by_count":32},{"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":"1704.05539","title":"Beating Atari with Natural Language Guided Reinforcement Learning","created":"2017-04-18","cited_by_count":24},{"id":"2209.04924","title":"Meta-Reinforcement Learning via Language Instructions","created":"2022-09-11","cited_by_count":18},{"id":"1910.07615","title":"Conditional Driving from Natural Language Instructions","created":"2019-10-16","cited_by_count":17},{"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":"2007.12770","title":"BabyAI 1.1","created":"2020-07-24","cited_by_count":8},{"id":"2303.05069","title":"Conceptual Reinforcement Learning for Language-Conditioned Tasks","created":"2023-03-09","cited_by_count":8},{"id":"2302.09368","title":"Natural Language-conditioned Reinforcement Learning with Inside-out Task Language Development and Translation","created":"2023-02-18","cited_by_count":7}],"next_cursor":null}