{"list":"other","total":108,"rows":[{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"1502.05477","title":"Trust Region Policy Optimization","created":"2015-02-19","cited_by_count":2580},{"id":"1606.03476","title":"Generative Adversarial Imitation Learning","created":"2016-06-10","cited_by_count":1597},{"id":"1611.08050","title":"Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields","created":"2016-11-24","cited_by_count":1064},{"id":"1604.07316","title":"End to End Learning for Self-Driving Cars","created":"2016-04-25","cited_by_count":1009},{"id":"1504.00702","title":"End-to-End Training of Deep Visuomotor Policies","created":"2015-04-02","cited_by_count":875},{"id":"1511.06581","title":"Dueling Network Architectures for Deep Reinforcement Learning","created":"2015-11-20","cited_by_count":785},{"id":"1709.06560","title":"Deep Reinforcement Learning that Matters","created":"2017-09-19","cited_by_count":754},{"id":"1703.10593","title":"Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks","created":"2017-03-30","cited_by_count":707},{"id":"1802.03601","title":"Deep Visual Domain Adaptation: A Survey","created":"2018-02-10","cited_by_count":635},{"id":"1805.01954","title":"Behavioral Cloning from Observation","created":"2018-05-04","cited_by_count":492},{"id":"1710.11248","title":"Learning Robust Rewards with Adversarial Inverse Reinforcement Learning","created":"2017-10-30","cited_by_count":490},{"id":"1710.02410","title":"End-to-end Driving via Conditional Imitation Learning","created":"2017-10-06","cited_by_count":485},{"id":"1704.06888","title":"Time-Contrastive Networks: Self-Supervised Learning from Video","created":"2017-04-23","cited_by_count":459},{"id":"1811.06711","title":"An Algorithmic Perspective on Imitation Learning","created":"2018-11-16","cited_by_count":459},{"id":"1805.08296","title":"Data-Efficient Hierarchical Reinforcement Learning","created":"2018-05-21","cited_by_count":455},{"id":"1609.05140","title":"The Option-Critic Architecture","created":"2016-09-16","cited_by_count":448},{"id":"1603.00448","title":"Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization","created":"2016-03-01","cited_by_count":406},{"id":"1910.11956","title":"Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learning","created":"2019-10-25","cited_by_count":384},{"id":"1703.01161","title":"FeUdal Networks for Hierarchical Reinforcement Learning","created":"2017-03-03","cited_by_count":337},{"id":"1811.06521","title":"Reward learning from human preferences and demonstrations in Atari","created":"2018-11-15","cited_by_count":316},{"id":"1606.03137","title":"Cooperative Inverse Reinforcement Learning","created":"2016-06-09","cited_by_count":300},{"id":"1806.06877","title":"A Survey of Inverse Reinforcement Learning: Challenges, Methods and Progress","created":"2018-06-18","cited_by_count":298},{"id":"1612.07828","title":"Learning from Simulated and Unsupervised Images through Adversarial Training","created":"2016-12-22","cited_by_count":288},{"id":"1604.06057","title":"Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation","created":"2016-04-20","cited_by_count":286},{"id":"1709.06009","title":"Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents","created":"2017-09-18","cited_by_count":269},{"id":"1807.01281","title":"Human-level performance in first-person multiplayer games with population-based deep reinforcement learning","created":"2018-07-03","cited_by_count":264},{"id":"1904.06387","title":"Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observations","created":"2019-04-12","cited_by_count":260},{"id":"1809.02925","title":"Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learning","created":"2018-09-09","cited_by_count":204},{"id":"1611.01796","title":"Modular Multitask Reinforcement Learning with Policy Sketches","created":"2016-11-06","cited_by_count":203},{"id":"1406.2807","title":"The Secrets of Salient Object Segmentation","created":"2014-06-11","cited_by_count":200},{"id":"1604.03605","title":"What do different evaluation metrics tell us about saliency models?","created":"2016-04-12","cited_by_count":185},{"id":"1807.06158","title":"Generative Adversarial Imitation from Observation","created":"2018-07-17","cited_by_count":184},{"id":"1810.05587","title":"A Survey and Critique of Multiagent Deep Reinforcement Learning","created":"2018-10-12","cited_by_count":177},{"id":"1707.03374","title":"Imitation from Observation: Learning to Imitate Behaviors from Raw Video via Context Translation","created":"2017-07-11","cited_by_count":167},{"id":"1804.02717","title":"DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skills","created":"2018-04-08","cited_by_count":163},{"id":"1701.06049","title":"Interactive Learning from Policy-Dependent Human Feedback","created":"2017-01-21","cited_by_count":158},{"id":"1606.05814","title":"Eye Tracking for Everyone","created":"2016-06-18","cited_by_count":155},{"id":"1504.02863","title":"Appearance-Based Gaze Estimation in the Wild","created":"2015-04-11","cited_by_count":153},{"id":"1501.02741","title":"Salient Object Detection: A Benchmark","created":"2015-01-05","cited_by_count":131},{"id":"1709.10163","title":"Deep TAMER: Interactive Agent Shaping in High-Dimensional State Spaces","created":"2017-09-28","cited_by_count":123},{"id":"1711.09017","title":"MPIIGaze: Real-World Dataset and Deep Appearance-Based Gaze Estimation","created":"2017-11-24","cited_by_count":118},{"id":"1804.08606","title":"Zero-Shot Visual Imitation","created":"2018-04-23","cited_by_count":117},{"id":"1703.01703","title":"Third-Person Imitation Learning","created":"2017-03-06","cited_by_count":103},{"id":"1707.05173","title":"Trial without Error: Towards Safe Reinforcement Learning via Human Intervention","created":"2017-07-17","cited_by_count":103},{"id":"1805.07914","title":"Imitating Latent Policies from Observation","created":"2018-05-21","cited_by_count":101},{"id":"1805.11592","title":"Playing hard exploration games by watching YouTube","created":"2018-05-29","cited_by_count":99},{"id":"1905.13566","title":"Recent Advances in Imitation Learning from Observation","created":"2019-05-30","cited_by_count":93},{"id":"2004.04650","title":"State-Only Imitation Learning for Dexterous Manipulation","created":"2020-04-07","cited_by_count":91},{"id":"2012.14176","title":"Deep Visual Domain Adaptation","created":"2020-12-28","cited_by_count":91},{"id":"1703.02018","title":"Combining Self-Supervised Learning and Imitation for Vision-Based Rope Manipulation","created":"2017-03-06","cited_by_count":90},{"id":"1803.00590","title":"Hierarchical Imitation and Reinforcement Learning","created":"2018-03-01","cited_by_count":88},{"id":"1810.04303","title":"Batch Active Preference-Based Learning of Reward Functions","created":"2018-10-10","cited_by_count":87},{"id":"1703.02949","title":"Learning Invariant Feature Spaces to Transfer Skills with Reinforcement Learning","created":"2017-03-08","cited_by_count":85},{"id":"2011.06507","title":"Reinforcement Learning with Videos: Combining Offline Observations with Interaction","created":"2020-11-12","cited_by_count":82},{"id":"1705.03854","title":"Predicting the Driver's Focus of Attention: the DR(eye)VE Project","created":"2017-05-10","cited_by_count":79},{"id":"1905.10948","title":"Provably Efficient Imitation Learning from Observation Alone","created":"2019-05-27","cited_by_count":78},{"id":"1707.02201","title":"Learning human behaviors from motion capture by adversarial imitation","created":"2017-07-07","cited_by_count":77},{"id":"1710.01813","title":"Neural Task Programming: Learning to Generalize Across Hierarchical Tasks","created":"2017-10-04","cited_by_count":76},{"id":"2005.02575","title":"Active Preference-Based Gaussian Process Regression for Reward Learning","created":"2020-05-06","cited_by_count":71},{"id":"2006.14091","title":"Learning Reward Functions from Diverse Sources of Human Feedback: Optimally Integrating Demonstrations and Preferences","created":"2020-06-24","cited_by_count":71},{"id":"1801.07424","title":"Revisiting Video Saliency: A Large-scale Benchmark and a New Model","created":"2018-01-23","cited_by_count":67},{"id":"1705.10479","title":"Multi-Modal Imitation Learning from Unstructured Demonstrations using Generative Adversarial Nets","created":"2017-05-30","cited_by_count":64},{"id":"1906.08928","title":"Learning Reward Functions by Integrating Human Demonstrations and Preferences","created":"2019-06-21","cited_by_count":64},{"id":"1711.06406","title":"Predicting Driver Attention in Critical Situations","created":"2017-11-17","cited_by_count":61},{"id":"1811.10698","title":"LSTA: Long Short-Term Attention for Egocentric Action Recognition","created":"2018-11-26","cited_by_count":57},{"id":"1902.04257","title":"Deep Reinforcement Learning from Policy-Dependent Human Feedback","created":"2019-02-12","cited_by_count":56},{"id":"1901.01874","title":"Mutual Context Network for Jointly Estimating Egocentric Gaze and Actions","created":"2019-01-07","cited_by_count":54},{"id":"1505.05916","title":"Rendering of Eyes for Eye-Shape Registration and Gaze Estimation","created":"2015-05-21","cited_by_count":49},{"id":"1807.10002","title":"Deep Pictorial Gaze Estimation","created":"2018-07-26","cited_by_count":49},{"id":"1910.04417","title":"Imitation Learning from Observations by Minimizing Inverse Dynamics Disagreement","created":"2019-10-10","cited_by_count":46},{"id":"1710.05421","title":"DDCO: Discovery of Deep Continuous Options for Robot Learning from Demonstrations","created":"2017-10-15","cited_by_count":43},{"id":"1909.09906","title":"Leveraging Human Guidance for Deep Reinforcement Learning Tasks","created":"2019-09-21","cited_by_count":42},{"id":"1810.01266","title":"Directed-Info GAIL: Learning Hierarchical Policies from Unsegmented Demonstrations using Directed Information","created":"2018-09-29","cited_by_count":41},{"id":"1810.11748","title":"DQN-TAMER: Human-in-the-Loop Reinforcement Learning with Intractable Feedback","created":"2018-10-28","cited_by_count":41},{"id":"1709.06683","title":"OptionGAN: Learning Joint Reward-Policy Options using Generative Adversarial Inverse Reinforcement Learning","created":"2017-09-20","cited_by_count":40},{"id":"2009.13649","title":"The EMPATHIC Framework for Task Learning from Implicit Human Feedback","created":"2020-09-28","cited_by_count":38},{"id":"1312.7570","title":"Actions in the Eye: Dynamic Gaze Datasets and Learnt Saliency Models for Visual Recognition","created":"2013-12-29","cited_by_count":37},{"id":"1809.06404","title":"Adversarial Imitation via Variational Inverse Reinforcement Learning","created":"2018-09-17","cited_by_count":36},{"id":"1808.00928","title":"Learning Actionable Representations from Visual Observations","created":"2018-08-02","cited_by_count":35},{"id":"1806.03960","title":"AGIL: Learning Attention from Human for Visuomotor Tasks","created":"2018-06-01","cited_by_count":32},{"id":"1909.10400","title":"Robot Navigation in Crowds by Graph Convolutional Networks with Attention Learned from Human Gaze","created":"2019-09-23","cited_by_count":30},{"id":"1701.04079","title":"Agent-Agnostic Human-in-the-Loop Reinforcement Learning","created":"2017-01-15","cited_by_count":23},{"id":"1905.09335","title":"Imitation Learning from Video by Leveraging Proprioception","created":"2019-05-22","cited_by_count":23},{"id":"1810.03599","title":"SFV: Reinforcement Learning of Physical Skills from Videos","created":"2018-10-08","cited_by_count":20},{"id":"1906.10187","title":"Learning to Interactively Learn and Assist","created":"2019-06-24","cited_by_count":20},{"id":"1903.09950","title":"Periphery-Fovea Multi-Resolution Driving Model guided by Human Attention","created":"2019-03-24","cited_by_count":19},{"id":"1906.07372","title":"RIDM: Reinforced Inverse Dynamics Modeling for Learning from a Single Observed Demonstration","created":"2019-06-18","cited_by_count":19},{"id":"1802.07606","title":"Ordered Preference Elicitation Strategies for Supporting Multi-Objective Decision Making","created":"2018-02-21","cited_by_count":18},{"id":"1901.03798","title":"3D Human Pose Machines with Self-supervised Learning","created":"2019-01-12","cited_by_count":17},{"id":"1806.11244","title":"One-Shot Learning of Multi-Step Tasks from Observation via Activity Localization in Auxiliary Video","created":"2018-06-29","cited_by_count":16},{"id":"1903.04110","title":"Hybrid Reinforcement Learning with Expert State Sequences","created":"2019-03-11","cited_by_count":14},{"id":"1904.02209","title":"The Green Choice: Learning and Influencing Human Decisions on Shared Roads","created":"2019-04-03","cited_by_count":14},{"id":"1903.02501","title":"Understanding and Visualizing Deep Visual Saliency Models","created":"2019-03-06","cited_by_count":13},{"id":"1910.00682","title":"Accelerated Robot Learning via Human Brain Signals","created":"2019-10-01","cited_by_count":13},{"id":"1806.01267","title":"Internal Model from Observations for Reward Shaping","created":"2018-06-02","cited_by_count":11},{"id":"1904.06090","title":"Digging Deeper into Egocentric Gaze Prediction","created":"2019-04-12","cited_by_count":11},{"id":"1904.08377","title":"Gaze Training by Modulated Dropout Improves Imitation Learning","created":"2019-04-17","cited_by_count":10},{"id":"2105.01850","title":"Preference learning along multiple criteria: A game-theoretic perspective","created":"2021-05-05","cited_by_count":9},{"id":"1810.11545","title":"Efficiently Combining Human Demonstrations and Interventions for Safe Training of Autonomous Systems in Real-Time","created":"2018-10-26","cited_by_count":8}],"next_cursor":"100"}