{"list":"other","total":84,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1612.01474","title":"Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles","created":"2016-12-05","cited_by_count":3926},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920},{"id":"1912.01603","title":"Dream to Control: Learning Behaviors by Latent Imagination","created":"2019-12-03","cited_by_count":1653},{"id":"1606.06565","title":"Concrete Problems in AI Safety","created":"2016-06-21","cited_by_count":1642},{"id":"1610.01644","title":"Understanding intermediate layers using linear classifier probes","created":"2016-10-05","cited_by_count":1353},{"id":"1905.02175","title":"Adversarial Examples Are Not Bugs, They Are Features","created":"2019-05-06","cited_by_count":953},{"id":"1809.01999","title":"Recurrent World Models Facilitate Policy Evolution","created":"2018-09-04","cited_by_count":785},{"id":"2004.04136","title":"CURL: Contrastive Unsupervised Representations for Reinforcement Learning","created":"2020-04-08","cited_by_count":760},{"id":"1802.06070","title":"Diversity is All You Need: Learning Skills without a Reward Function","created":"2018-02-16","cited_by_count":752},{"id":"1706.08498","title":"Spectrally-normalized margin bounds for neural networks","created":"2017-06-26","cited_by_count":686},{"id":"2109.12098","title":"CLIPort: What and Where Pathways for Robotic Manipulation","created":"2021-09-24","cited_by_count":622},{"id":"1805.01954","title":"Behavioral Cloning from Observation","created":"2018-05-04","cited_by_count":492},{"id":"1811.06711","title":"An Algorithmic Perspective on Imitation Learning","created":"2018-11-16","cited_by_count":459},{"id":"2006.10742","title":"Learning Invariant Representations for Reinforcement Learning without Reconstruction","created":"2020-06-18","cited_by_count":436},{"id":"1603.00448","title":"Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization","created":"2016-03-01","cited_by_count":406},{"id":"2206.11795","title":"Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos","created":"2022-06-23","cited_by_count":345},{"id":"1811.06521","title":"Reward learning from human preferences and demonstrations in Atari","created":"2018-11-15","cited_by_count":316},{"id":"1903.01973","title":"Learning Latent Plans from Play","created":"2019-03-05","cited_by_count":316},{"id":"2106.05091","title":"PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-training","created":"2021-06-09","cited_by_count":302},{"id":"1710.04615","title":"Deep Imitation Learning for Complex Manipulation Tasks from Virtual Reality Teleoperation","created":"2017-10-12","cited_by_count":289},{"id":"1905.11979","title":"Causal Confusion in Imitation Learning","created":"2019-05-28","cited_by_count":288},{"id":"1506.07365","title":"Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images","created":"2015-06-24","cited_by_count":274},{"id":"2009.08319","title":"Decoupling Representation Learning from Reinforcement Learning","created":"2020-09-14","cited_by_count":269},{"id":"1503.00759","title":"A Review of Relational Machine Learning for Knowledge Graphs","created":"2015-03-02","cited_by_count":265},{"id":"1711.02827","title":"Inverse Reward Design","created":"2017-11-08","cited_by_count":249},{"id":"1511.00830","title":"The Variational Fair Autoencoder","created":"2015-11-03","cited_by_count":223},{"id":"2002.09434","title":"Few-Shot Learning via Learning the Representation, Provably","created":"2020-02-21","cited_by_count":214},{"id":"2011.13377","title":"How Well Do Self-Supervised Models Transfer?","created":"2020-11-26","cited_by_count":213},{"id":"2202.13903","title":"Bayesian Structure Learning with Generative Flow Networks","created":"2022-02-28","cited_by_count":153},{"id":"1707.08475","title":"DARLA: Improving Zero-Shot Transfer in Reinforcement Learning","created":"2017-07-26","cited_by_count":149},{"id":"1906.08226","title":"Unsupervised State Representation Learning in Atari","created":"2019-06-19","cited_by_count":144},{"id":"1711.00138","title":"Visualizing and Understanding Atari Agents","created":"2017-10-31","cited_by_count":141},{"id":"1802.04181","title":"State Representation Learning for Control: An Overview","created":"2018-02-12","cited_by_count":127},{"id":"1709.10163","title":"Deep TAMER: Interactive Agent Shaping in High-Dimensional State Spaces","created":"2017-09-28","cited_by_count":123},{"id":"1904.07854","title":"End-to-End Robotic Reinforcement Learning without Reward Engineering","created":"2019-04-16","cited_by_count":122},{"id":"2106.04799","title":"Pretraining Representations for Data-Efficient Reinforcement Learning","created":"2021-06-09","cited_by_count":105},{"id":"1906.05237","title":"Reinforcement Knowledge Graph Reasoning for Explainable Recommendation","created":"2019-06-12","cited_by_count":102},{"id":"1707.02920","title":"Vision-Based Multi-Task Manipulation for Inexpensive Robots Using End-To-End Learning from Demonstration","created":"2017-07-10","cited_by_count":100},{"id":"1805.11592","title":"Playing hard exploration games by watching YouTube","created":"2018-05-29","cited_by_count":99},{"id":"2102.05815","title":"Representation Matters: Offline Pretraining for Sequential Decision Making","created":"2021-02-11","cited_by_count":91},{"id":"2103.12718","title":"Self-Supervised Pretraining Improves Self-Supervised Pretraining","created":"2021-03-23","cited_by_count":82},{"id":"2007.00631","title":"Causal Discovery in Physical Systems from Videos","created":"2020-07-01","cited_by_count":77},{"id":"2002.09089","title":"Safe Imitation Learning via Fast Bayesian Reward Inference from Preferences","created":"2020-02-21","cited_by_count":73},{"id":"2112.13112","title":"A Survey on Interpretable Reinforcement Learning","created":"2021-12-24","cited_by_count":73},{"id":"2111.00876","title":"On the Expressivity of Markov Reward","created":"2021-11-01","cited_by_count":71},{"id":"1805.11686","title":"Variational Inverse Control with Events: A General Framework for Data-Driven Reward Definition","created":"2018-05-29","cited_by_count":69},{"id":"1811.07819","title":"Learning Actionable Representations with Goal-Conditioned Policies","created":"2018-11-19","cited_by_count":54},{"id":"1909.09314","title":"Meta-Inverse Reinforcement Learning with Probabilistic Context Variables","created":"2019-09-20","cited_by_count":50},{"id":"2109.03891","title":"SORNet: Spatial Object-Centric Representations for Sequential Manipulation","created":"2021-09-08","cited_by_count":48},{"id":"1912.05652","title":"Learning Human Objectives by Evaluating Hypothetical Behavior","created":"2019-12-05","cited_by_count":41},{"id":"2002.10544","title":"Provable Representation Learning for Imitation Learning via Bi-level Optimization","created":"2020-02-24","cited_by_count":41},{"id":"1706.00155","title":"Shared Autonomy via Hindsight Optimization for Teleoperation and Teaming","created":"2017-06-01","cited_by_count":40},{"id":"1805.12573","title":"Learning a Prior over Intent via Meta-Inverse Reinforcement Learning","created":"2018-05-31","cited_by_count":36},{"id":"2101.05850","title":"Continual Learning of Knowledge Graph Embeddings","created":"2021-01-14","cited_by_count":35},{"id":"1601.00741","title":"Learning Preferences for Manipulation Tasks from Online Coactive Feedback","created":"2016-01-05","cited_by_count":31},{"id":"2006.13208","title":"Feature Expansive Reward Learning: Rethinking Human Input","created":"2020-06-23","cited_by_count":25},{"id":"2108.12062","title":"Predicting Stable Configurations for Semantic Placement of Novel Objects","created":"2021-08-26","cited_by_count":24},{"id":"2003.02636","title":"Scalable Multi-Task Imitation Learning with Autonomous Improvement","created":"2020-02-25","cited_by_count":21},{"id":"1805.08882","title":"Multi-task Maximum Entropy Inverse Reinforcement Learning","created":"2018-05-22","cited_by_count":20},{"id":"2002.00941","title":"Quantifying Hypothesis Space Misspecification in Learning from Human-Robot Demonstrations and Physical Corrections","created":"2020-02-03","cited_by_count":19},{"id":"1905.12686","title":"Learning Representations by Humans, for Humans","created":"2019-05-29","cited_by_count":18},{"id":"2009.04743","title":"TripleTree: A Versatile Interpretable Representation of Black Box Agents and their Environments","created":"2020-09-10","cited_by_count":18},{"id":"2201.07082","title":"Inducing Structure in Reward Learning by Learning Features","created":"2022-01-18","cited_by_count":16},{"id":"1806.02454","title":"Including Uncertainty when Learning from Human Corrections","created":"2018-06-06","cited_by_count":15},{"id":"1904.01575","title":"Contrastive Predictive Coding Based Feature for Automatic Speaker Verification","created":"2019-04-01","cited_by_count":15},{"id":"2104.06556","title":"Situational Confidence Assistance for Lifelong Shared Autonomy","created":"2021-04-14","cited_by_count":15},{"id":"2205.07886","title":"An Empirical Investigation of Representation Learning for Imitation","created":"2022-05-16","cited_by_count":15},{"id":"1810.05157","title":"Learning under Misspecified Objective Spaces","created":"2018-10-11","cited_by_count":14},{"id":"2301.00810","title":"SIRL: Similarity-based Implicit Representation Learning","created":"2023-01-02","cited_by_count":14},{"id":"1412.0691","title":"RoboBrain: Large-Scale Knowledge Engine for Robots","created":"2014-12-01","cited_by_count":13},{"id":"1810.08167","title":"Expressing Robot Incapability","created":"2018-10-18","cited_by_count":13},{"id":"2111.05251","title":"Learning Perceptual Concepts by Bootstrapping from Human Queries","created":"2021-11-09","cited_by_count":12},{"id":"2103.05661","title":"On complementing end-to-end human behavior predictors with planning","created":"2021-03-09","cited_by_count":10},{"id":"1907.13627","title":"Disentangled Relational Representations for Explaining and Learning from Demonstration","created":"2019-07-31","cited_by_count":8},{"id":"2105.04484","title":"Towards Robust One-shot Task Execution using Knowledge Graph Embeddings","created":"2021-05-10","cited_by_count":8},{"id":"2108.04219","title":"Pragmatic Image Compression for Human-in-the-Loop Decision-Making","created":"2021-07-07","cited_by_count":7},{"id":"2203.07558","title":"Learning for Robot Decision Making under Distribution Shift: A Survey","created":"2022-03-14","cited_by_count":7},{"id":"2203.02091","title":"Teaching Robots to Span the Space of Functional Expressive Motion","created":"2022-03-04","cited_by_count":6},{"id":"2205.01836","title":"Explainable Knowledge Graph Embedding: Inference Reconciliation for Knowledge Inferences Supporting Robot Actions","created":"2022-05-04","cited_by_count":5},{"id":"2103.08008","title":"Meta Preference Learning for Fast User Adaptation in Human-Supervisory Multi-Robot Deployments","created":"2021-03-14","cited_by_count":3}],"next_cursor":null}