{"list":"other","total":76,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"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":"1801.01290","title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","created":"2018-01-04","cited_by_count":4885},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"1709.07871","title":"FiLM: Visual Reasoning with a General Conditioning Layer","created":"2017-09-22","cited_by_count":2333},{"id":"1506.02438","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","created":"2015-06-08","cited_by_count":2026},{"id":"1606.01540","title":"OpenAI Gym","created":"2016-06-05","cited_by_count":1736},{"id":"1703.06907","title":"Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World","created":"2017-03-20","cited_by_count":1498},{"id":"1609.09106","title":"HyperNetworks","created":"2016-09-27","cited_by_count":1027},{"id":"2205.06175","title":"A Generalist Agent","created":"2022-05-12","cited_by_count":808},{"id":"1910.07113","title":"Solving Rubik's Cube with a Robot Hand","created":"2019-10-16","cited_by_count":734},{"id":"1808.00177","title":"Learning Dexterous In-Hand Manipulation","created":"2018-08-01","cited_by_count":687},{"id":"1710.06537","title":"Sim-to-Real Transfer of Robotic Control with Dynamics Randomization","created":"2017-10-18","cited_by_count":672},{"id":"2112.04482","title":"FLAVA: A Foundational Language And Vision Alignment Model","created":"2021-12-08","cited_by_count":649},{"id":"1705.08045","title":"Learning multiple visual domains with residual adapters","created":"2017-05-22","cited_by_count":557},{"id":"2107.04034","title":"RMA: Rapid Motor Adaptation for Legged Robots","created":"2021-07-08","cited_by_count":508},{"id":"1611.02779","title":"RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning","created":"2016-11-09","cited_by_count":503},{"id":"1703.02702","title":"Robust Adversarial Reinforcement Learning","created":"2017-03-08","cited_by_count":451},{"id":"2005.00052","title":"MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfer","created":"2020-04-30","cited_by_count":445},{"id":"2007.07779","title":"AdapterHub: A Framework for Adapting Transformers","created":"2020-07-15","cited_by_count":444},{"id":"2009.13303","title":"Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Survey","created":"2020-09-24","cited_by_count":413},{"id":"1903.08254","title":"Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables","created":"2019-03-19","cited_by_count":389},{"id":"2302.09419","title":"A Comprehensive Survey on Pretrained Foundation Models: A History from BERT to ChatGPT","created":"2023-02-18","cited_by_count":368},{"id":"1812.02341","title":"Quantifying Generalization in Reinforcement Learning","created":"2018-12-06","cited_by_count":352},{"id":"2106.04489","title":"Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworks","created":"2021-06-08","cited_by_count":284},{"id":"1803.11347","title":"Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learning","created":"2018-03-30","cited_by_count":276},{"id":"2004.00784","title":"Learning Agile Robotic Locomotion Skills by Imitating Animals","created":"2020-04-02","cited_by_count":251},{"id":"1806.01242","title":"Graph networks as learnable physics engines for inference and control","created":"2018-06-04","cited_by_count":244},{"id":"1611.04201","title":"CAD2RL: Real Single-Image Flight without a Single Real Image","created":"2016-11-13","cited_by_count":233},{"id":"1502.02259","title":"Contextual Markov Decision Processes","created":"2015-02-08","cited_by_count":220},{"id":"1910.08348","title":"VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning","created":"2019-10-18","cited_by_count":217},{"id":"2102.06177","title":"Multi-Task Reinforcement Learning with Context-based Representations","created":"2021-02-11","cited_by_count":174},{"id":"2111.09794","title":"A Survey of Zero-shot Generalisation in Deep Reinforcement Learning","created":"2021-11-18","cited_by_count":170},{"id":"2303.04129","title":"Foundation Models for Decision Making: Problems, Methods, and Opportunities","created":"2023-03-07","cited_by_count":164},{"id":"2103.10427","title":"The Low-Rank Simplicity Bias in Deep Networks","created":"2021-03-18","cited_by_count":154},{"id":"1702.02453","title":"Preparing for the Unknown: Learning a Universal Policy with Online System Identification","created":"2017-02-08","cited_by_count":141},{"id":"1810.12282","title":"Assessing Generalization in Deep Reinforcement Learning","created":"2018-10-29","cited_by_count":133},{"id":"1806.07851","title":"Sim-to-Real Reinforcement Learning for Deformable Object Manipulation","created":"2018-06-20","cited_by_count":131},{"id":"2306.11706","title":"RoboCat: A Self-Improving Generalist Agent for Robotic Manipulation","created":"2023-06-20","cited_by_count":111},{"id":"2301.08028","title":"A Tutorial on Meta-Reinforcement Learning","created":"2023-01-19","cited_by_count":108},{"id":"1910.12911","title":"Generalization in Reinforcement Learning with Selective Noise Injection and Information Bottleneck","created":"2019-10-28","cited_by_count":101},{"id":"2005.06800","title":"Context-aware Dynamics Model for Generalization in Model-Based Reinforcement Learning","created":"2020-05-14","cited_by_count":98},{"id":"2203.11931","title":"MetaMorph: Learning Universal Controllers with Transformers","created":"2022-03-22","cited_by_count":89},{"id":"1806.07937","title":"A Dissection of Overfitting and Generalization in Continuous Reinforcement Learning","created":"2018-06-20","cited_by_count":87},{"id":"1906.07516","title":"Robust Reinforcement Learning for Continuous Control with Model Misspecification","created":"2019-06-18","cited_by_count":78},{"id":"2110.05457","title":"Legged Robots that Keep on Learning: Fine-Tuning Locomotion Policies in the Real World","created":"2021-10-11","cited_by_count":71},{"id":"1907.13196","title":"Wasserstein Robust Reinforcement Learning","created":"2019-07-30","cited_by_count":54},{"id":"2106.01463","title":"Lightweight Adapter Tuning for Multilingual Speech Translation","created":"2021-06-02","cited_by_count":54},{"id":"2009.09139","title":"Conditionally Adaptive Multi-Task Learning: Improving Transfer Learning in NLP Using Fewer Parameters & Less Data","created":"2020-09-19","cited_by_count":50},{"id":"2209.05309","title":"GenLoco: Generalized Locomotion Controllers for Quadrupedal Robots","created":"2022-09-12","cited_by_count":48},{"id":"1811.09864","title":"Hardware Conditioned Policies for Multi-Robot Transfer Learning","created":"2018-11-24","cited_by_count":46},{"id":"2202.04500","title":"Contextualize Me -- The Case for Context in Reinforcement Learning","created":"2022-02-09","cited_by_count":46},{"id":"2301.09816","title":"SMART: Self-supervised Multi-task pretrAining with contRol Transformers","created":"2023-01-24","cited_by_count":44},{"id":"2106.02940","title":"Same State, Different Task: Continual Reinforcement Learning without Interference","created":"2021-06-05","cited_by_count":43},{"id":"2104.05632","title":"Augmented World Models Facilitate Zero-Shot Dynamics Generalization From a Single Offline Environment","created":"2021-04-12","cited_by_count":42},{"id":"2210.11348","title":"Hypernetworks in Meta-Reinforcement Learning","created":"2022-10-20","cited_by_count":42},{"id":"1907.11740","title":"Environment Probing Interaction Policies","created":"2019-07-26","cited_by_count":39},{"id":"2010.13303","title":"Trajectory-wise Multiple Choice Learning for Dynamics Generalization in Reinforcement Learning","created":"2020-10-26","cited_by_count":35},{"id":"2106.06842","title":"Recomposing the Reinforcement Learning Building Blocks with Hypernetworks","created":"2021-06-12","cited_by_count":35},{"id":"2202.03218","title":"Efficient Adapter Transfer of Self-Supervised Speech Models for Automatic Speech Recognition","created":"2022-02-07","cited_by_count":32},{"id":"2109.03214","title":"Robust Predictable Control","created":"2021-09-07","cited_by_count":29},{"id":"2205.00305","title":"AdapterBias: Parameter-efficient Token-dependent Representation Shift for Adapters in NLP Tasks","created":"2022-04-30","cited_by_count":29},{"id":"2010.01062","title":"Exploration in Approximate Hyper-State Space for Meta Reinforcement Learning","created":"2020-10-02","cited_by_count":28},{"id":"2101.00420","title":"Learning to Generate Task-Specific Adapters from Task Description","created":"2021-01-02","cited_by_count":28},{"id":"2008.00614","title":"Dynamics Generalization via Information Bottleneck in Deep Reinforcement Learning","created":"2020-08-03","cited_by_count":26},{"id":"2110.06972","title":"Block Contextual MDPs for Continual Learning","created":"2021-10-13","cited_by_count":25},{"id":"2305.10912","title":"A Generalist Dynamics Model for Control","created":"2023-05-18","cited_by_count":24},{"id":"2203.08304","title":"Hyperdecoders: Instance-specific decoders for multi-task NLP","created":"2022-03-15","cited_by_count":22},{"id":"1612.00429","title":"Generalizing Skills with Semi-Supervised Reinforcement Learning","created":"2016-12-01","cited_by_count":18},{"id":"2011.05513","title":"Zero-Shot Terrain Generalization for Visual Locomotion Policies","created":"2020-11-11","cited_by_count":13},{"id":"2003.01373","title":"Learning Context-aware Task Reasoning for Efficient Meta-reinforcement Learning","created":"2020-03-03","cited_by_count":11},{"id":"2101.04750","title":"Linear Representation Meta-Reinforcement Learning for Instant Adaptation","created":"2021-01-12","cited_by_count":9},{"id":"2111.12146","title":"Sharing to learn and learning to share; Fitting together Meta-Learning, Multi-Task Learning, and Transfer Learning: A meta review","created":"2021-11-23","cited_by_count":6},{"id":"2109.08342","title":"Dropout's Dream Land: Generalization from Learned Simulators to Reality","created":"2021-09-17","cited_by_count":3}],"next_cursor":null}