{"list":"other","total":64,"rows":[{"id":"2004.05439","title":"Meta-Learning in Neural Networks: A Survey","created":"2020-04-11","cited_by_count":950},{"id":"2009.00236","title":"A Survey of Deep Active Learning","created":"2020-08-30","cited_by_count":554},{"id":"1708.05866","title":"A Brief Survey of Deep Reinforcement Learning","created":"2017-08-19","cited_by_count":483},{"id":"1811.06711","title":"An Algorithmic Perspective on Imitation Learning","created":"2018-11-16","cited_by_count":459},{"id":"1806.06877","title":"A Survey of Inverse Reinforcement Learning: Challenges, Methods and Progress","created":"2018-06-18","cited_by_count":298},{"id":"1802.07740","title":"Machine Theory of Mind","created":"2018-02-21","cited_by_count":226},{"id":"2010.09890","title":"Watch-And-Help: A Challenge for Social Perception and Human-AI Collaboration","created":"2020-10-19","cited_by_count":133},{"id":"2103.05668","title":"Core Challenges of Social Robot Navigation: A Survey","created":"2021-03-09","cited_by_count":106},{"id":"1903.12220","title":"The Algorithmic Automation Problem: Prediction, Triage, and Human Effort","created":"2019-03-28","cited_by_count":101},{"id":"2011.06619","title":"Learning Latent Representations to Influence Multi-Agent Interaction","created":"2020-11-12","cited_by_count":93},{"id":"1910.12179","title":"BAIL: Best-Action Imitation Learning for Batch Deep Reinforcement Learning","created":"2019-10-27","cited_by_count":91},{"id":"2007.08794","title":"Discovering Reinforcement Learning Algorithms","created":"2020-07-17","cited_by_count":77},{"id":"2006.07532","title":"Online Bayesian Goal Inference for Boundedly-Rational Planning Agents","created":"2020-06-13","cited_by_count":68},{"id":"2011.04709","title":"f-IRL: Inverse Reinforcement Learning via State Marginal Matching","created":"2020-11-09","cited_by_count":67},{"id":"1802.01744","title":"Shared Autonomy via Deep Reinforcement Learning","created":"2018-02-06","cited_by_count":66},{"id":"2010.05772","title":"AttendLight: Universal Attention-Based Reinforcement Learning Model for Traffic Signal Control","created":"2020-10-12","cited_by_count":62},{"id":"1907.09620","title":"Rapid trial-and-error learning with simulation supports flexible tool use and physical reasoning","created":"2019-07-22","cited_by_count":61},{"id":"2002.11089","title":"Rewriting History with Inverse RL: Hindsight Inference for Policy Improvement","created":"2020-02-25","cited_by_count":60},{"id":"1810.06721","title":"Optimizing Agent Behavior over Long Time Scales by Transporting Value","created":"2018-10-15","cited_by_count":58},{"id":"2005.14310","title":"Predicting Goal-directed Human Attention Using Inverse Reinforcement Learning","created":"2020-05-28","cited_by_count":53},{"id":"2010.09034","title":"Model-Based Inverse Reinforcement Learning from Visual Demonstrations","created":"2020-10-18","cited_by_count":52},{"id":"1910.01077","title":"Task-Relevant Adversarial Imitation Learning","created":"2019-10-02","cited_by_count":45},{"id":"2006.06412","title":"Modeling Human Driving Behavior through Generative Adversarial Imitation Learning","created":"2020-06-10","cited_by_count":45},{"id":"2011.13464","title":"Meta-learning in natural and artificial intelligence","created":"2020-11-26","cited_by_count":39},{"id":"2105.03354","title":"The future of human-AI collaboration: a taxonomy of design knowledge for hybrid intelligence systems","created":"2021-05-07","cited_by_count":39},{"id":"2010.11223","title":"Meta-trained agents implement Bayes-optimal agents","created":"2020-10-21","cited_by_count":38},{"id":"1910.13406","title":"Generalization of Reinforcement Learners with Working and Episodic Memory","created":"2019-10-29","cited_by_count":36},{"id":"2105.10614","title":"Human-AI Collaboration with Bandit Feedback","created":"2021-05-22","cited_by_count":36},{"id":"1901.06085","title":"Theory of Minds: Understanding Behavior in Groups Through Inverse Planning","created":"2019-01-18","cited_by_count":30},{"id":"2003.11778","title":"Too many cooks: Bayesian inference for coordinating multi-agent collaboration","created":"2020-03-26","cited_by_count":29},{"id":"1906.00889","title":"Learning to solve the credit assignment problem","created":"2019-06-03","cited_by_count":27},{"id":"1902.09641","title":"Stochastic Prediction of Multi-Agent Interactions from Partial Observations","created":"2019-02-25","cited_by_count":26},{"id":"2005.11016","title":"Reinforcement learning with human advice: a survey","created":"2020-05-22","cited_by_count":24},{"id":"2106.11650","title":"A Survey on Human-aware Robot Navigation","created":"2021-06-22","cited_by_count":24},{"id":"2006.11441","title":"Task-Agnostic Online Reinforcement Learning with an Infinite Mixture of Gaussian Processes","created":"2020-06-19","cited_by_count":23},{"id":"2110.07448","title":"Human-robot collaboration and machine learning: a systematic review of recent research","created":"2021-10-14","cited_by_count":20},{"id":"2008.01712","title":"Deep Inverse Q-learning with Constraints","created":"2020-08-04","cited_by_count":17},{"id":"2010.10341","title":"Learning to Learn Variational Semantic Memory","created":"2020-10-20","cited_by_count":17},{"id":"2011.08541","title":"Efficient Exploration of Reward Functions in Inverse Reinforcement Learning via Bayesian Optimization","created":"2020-11-17","cited_by_count":16},{"id":"1711.06892","title":"Learning to select computations","created":"2017-11-18","cited_by_count":15},{"id":"1903.10545","title":"Winning Isn't Everything: Enhancing Game Development with Intelligent Agents","created":"2019-03-25","cited_by_count":15},{"id":"1910.07089","title":"Challenges of Human-Aware AI Systems","created":"2019-10-15","cited_by_count":13},{"id":"2104.02938","title":"Deep Interpretable Models of Theory of Mind","created":"2021-04-07","cited_by_count":13},{"id":"2011.04816","title":"StylePredict: Machine Theory of Mind for Human Driver Behavior From Trajectories","created":"2020-11-09","cited_by_count":11},{"id":"2001.08301","title":"How to Support Users in Understanding Intelligent Systems? Structuring the Discussion","created":"2020-01-22","cited_by_count":9},{"id":"2007.06703","title":"Learning Retrospective Knowledge with Reverse Reinforcement Learning","created":"2020-07-09","cited_by_count":8},{"id":"2103.09990","title":"Human-AI Symbiosis: A Survey of Current Approaches","created":"2021-03-18","cited_by_count":8},{"id":"2007.07812","title":"Inverse Reinforcement Learning from a Gradient-based Learner","created":"2020-07-15","cited_by_count":7},{"id":"2102.06755","title":"Unpacking Human Teachers' Intentions For Natural Interactive Task Learning","created":"2021-02-12","cited_by_count":6},{"id":"1909.00193","title":"Functional advantages of an adaptive Theory of Mind for robotics: a review of current architectures","created":"2019-08-31","cited_by_count":4},{"id":"2006.07777","title":"Active Imitation Learning from Multiple Non-Deterministic Teachers: Formulation, Challenges, and Algorithms","created":"2020-06-14","cited_by_count":4},{"id":"2010.04466","title":"Learning Not to Learn: Nature versus Nurture in Silico","created":"2020-10-09","cited_by_count":4},{"id":"2010.04605","title":"Instance Weighted Incremental Evolution Strategies for Reinforcement Learning in Dynamic Environments","created":"2020-10-09","cited_by_count":4},{"id":"2103.16168","title":"Understanding Mental Models of AI through Player-AI Interaction","created":"2021-03-30","cited_by_count":4},{"id":"2104.03946","title":"Learning What To Do by Simulating the Past","created":"2021-04-08","cited_by_count":4},{"id":"1905.13225","title":"Modeling Theory of Mind in Multi-Agent Games Using Adaptive Feedback Control","created":"2019-05-29","cited_by_count":3},{"id":"1906.00535","title":"Towards Interactive Training of Non-Player Characters in Video Games","created":"2019-06-03","cited_by_count":3},{"id":"2002.11637","title":"Learning Navigation Costs from Demonstration in Partially Observable Environments","created":"2020-02-26","cited_by_count":3},{"id":"2009.09266","title":"Humans learn too: Better Human-AI Interaction using Optimized Human Inputs","created":"2020-09-19","cited_by_count":3},{"id":"2003.04203","title":"Human AI interaction loop training: New approach for interactive reinforcement learning","created":"2020-03-09","cited_by_count":2},{"id":"2011.07193","title":"Data-Efficient Learning for Complex and Real-Time Physical Problem Solving using Augmented Simulation","created":"2020-11-14","cited_by_count":2},{"id":"1909.03868","title":"Partner Approximating Learners (PAL): Simulation-Accelerated Learning with Explicit Partner Modeling in Multi-Agent Domains","created":"2019-09-09","cited_by_count":1},{"id":"2001.06793","title":"Learning Options from Demonstration using Skill Segmentation","created":"2020-01-19","cited_by_count":1},{"id":"2012.07330","title":"Active Hierarchical Imitation and Reinforcement Learning","created":"2020-12-14","cited_by_count":1}],"next_cursor":null}