{"list":"other","total":54,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"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":"1512.04150","title":"Learning Deep Features for Discriminative Localization","created":"2015-12-14","cited_by_count":2436},{"id":"1506.02438","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","created":"2015-06-08","cited_by_count":2026},{"id":"1905.00414","title":"Similarity of Neural Network Representations Revisited","created":"2019-05-01","cited_by_count":1755},{"id":"1707.01495","title":"Hindsight Experience Replay","created":"2017-07-05","cited_by_count":1136},{"id":"1604.07316","title":"End to End Learning for Self-Driving Cars","created":"2016-04-25","cited_by_count":1009},{"id":"2010.11251","title":"Learning Quadrupedal Locomotion over Challenging Terrain","created":"2020-10-21","cited_by_count":604},{"id":"2109.11978","title":"Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learning","created":"2021-09-24","cited_by_count":512},{"id":"2107.04034","title":"RMA: Rapid Motor Adaptation for Legged Robots","created":"2021-07-08","cited_by_count":508},{"id":"1710.02410","title":"End-to-end Driving via Conditional Imitation Learning","created":"2017-10-06","cited_by_count":485},{"id":"1805.08296","title":"Data-Efficient Hierarchical Reinforcement Learning","created":"2018-05-21","cited_by_count":455},{"id":"2007.06600","title":"Closed-Form Factorization of Latent Semantics in GANs","created":"2020-07-13","cited_by_count":408},{"id":"1812.02341","title":"Quantifying Generalization in Reinforcement Learning","created":"2018-12-06","cited_by_count":352},{"id":"2109.12674","title":"MetaDrive: Composing Diverse Driving Scenarios for Generalizable Reinforcement Learning","created":"2021-09-26","cited_by_count":290},{"id":"1807.00412","title":"Learning to Drive in a Day","created":"2018-07-01","cited_by_count":273},{"id":"1810.02890","title":"HG-DAgger: Interactive Imitation Learning with Human Experts","created":"2018-10-05","cited_by_count":266},{"id":"2009.05041","title":"Understanding the Role of Individual Units in a Deep Neural Network","created":"2020-09-10","cited_by_count":255},{"id":"1802.00614","title":"Visual Interpretability for Deep Learning: a Survey","created":"2018-02-02","cited_by_count":155},{"id":"2110.05113","title":"Learning High-Speed Flight in the Wild","created":"2021-10-11","cited_by_count":128},{"id":"1709.10163","title":"Deep TAMER: Interactive Agent Shaping in High-Dimensional State Spaces","created":"2017-09-28","cited_by_count":123},{"id":"2012.06733","title":"Human-in-the-Loop Imitation Learning using Remote Teleoperation","created":"2020-12-12","cited_by_count":112},{"id":"1703.10631","title":"Interpretable Learning for Self-Driving Cars by Visualizing Causal Attention","created":"2017-03-30","cited_by_count":107},{"id":"1911.09267","title":"Semantic Hierarchy Emerges in Deep Generative Representations for Scene Synthesis","created":"2019-11-21","cited_by_count":106},{"id":"1707.05173","title":"Trial without Error: Towards Safe Reinforcement Learning via Human Intervention","created":"2017-07-17","cited_by_count":103},{"id":"1711.05611","title":"Interpreting Deep Visual Representations via Network Dissection","created":"2017-11-15","cited_by_count":103},{"id":"2010.13924","title":"Benchmarking Deep Learning Interpretability in Time Series Predictions","created":"2020-10-26","cited_by_count":102},{"id":"1811.11711","title":"Neural probabilistic motor primitives for humanoid control","created":"2018-11-28","cited_by_count":97},{"id":"1912.00177","title":"Urban Driving with Conditional Imitation Learning","created":"2019-11-30","cited_by_count":86},{"id":"2007.10379","title":"Generative Hierarchical Features from Synthesizing Images","created":"2020-07-20","cited_by_count":83},{"id":"2103.05154","title":"Explanations in Autonomous Driving: A Survey","created":"2021-03-09","cited_by_count":81},{"id":"2107.03996","title":"Learning Vision-Guided Quadrupedal Locomotion End-to-End with Cross-Modal Transformers","created":"2021-07-08","cited_by_count":79},{"id":"1802.01744","title":"Shared Autonomy via Deep Reinforcement Learning","created":"2018-02-06","cited_by_count":66},{"id":"1912.05743","title":"Exploratory Not Explanatory: Counterfactual Analysis of Saliency Maps for Deep Reinforcement Learning","created":"2019-12-09","cited_by_count":60},{"id":"1803.07770","title":"Emergence of grid-like representations by training recurrent neural networks to perform spatial localization","created":"2018-03-21","cited_by_count":52},{"id":"1912.12191","title":"Explain Your Move: Understanding Agent Actions Using Specific and Relevant Feature Attribution","created":"2019-12-23","cited_by_count":50},{"id":"1803.05580","title":"Feedback Control For Cassie With Deep Reinforcement Learning","created":"2018-03-15","cited_by_count":45},{"id":"1909.09906","title":"Leveraging Human Guidance for Deep Reinforcement Learning Tasks","created":"2019-09-21","cited_by_count":42},{"id":"1912.05652","title":"Learning Human Objectives by Evaluating Hypothetical Behavior","created":"2019-12-05","cited_by_count":41},{"id":"2005.03210","title":"Shared Autonomy with Learned Latent Actions","created":"2020-05-07","cited_by_count":34},{"id":"2110.06831","title":"Safe Driving via Expert Guided Policy Optimization","created":"2021-10-13","cited_by_count":31},{"id":"1805.08180","title":"Hierarchical Reinforcement Learning with Hindsight","created":"2018-05-21","cited_by_count":26},{"id":"1903.02090","title":"Open-Sourced Reinforcement Learning Environments for Surgical Robotics","created":"2019-03-05","cited_by_count":26},{"id":"2004.05097","title":"Residual Policy Learning for Shared Autonomy","created":"2020-04-10","cited_by_count":26},{"id":"2101.05507","title":"Evaluating the Robustness of Collaborative Agents","created":"2021-01-14","cited_by_count":25},{"id":"1911.09451","title":"Deep neuroethology of a virtual rodent","created":"2019-11-21","cited_by_count":23},{"id":"2007.00178","title":"Reinforcement Learning based Control of Imitative Policies for Near-Accident Driving","created":"2020-07-01","cited_by_count":23},{"id":"1903.05196","title":"A Review of Reinforcement Learning for Autonomous Building Energy Management","created":"2019-03-12","cited_by_count":21},{"id":"2010.15942","title":"Machine versus Human Attention in Deep Reinforcement Learning Tasks","created":"2020-10-29","cited_by_count":16},{"id":"2104.07246","title":"Human-in-the-Loop Deep Reinforcement Learning with Application to Autonomous Driving","created":"2021-04-15","cited_by_count":16},{"id":"1812.07069","title":"An Atari Model Zoo for Analyzing, Visualizing, and Comparing Deep Reinforcement Learning Agents","created":"2018-12-17","cited_by_count":15},{"id":"2107.05825","title":"Recent Advances in Leveraging Human Guidance for Sequential Decision-Making Tasks","created":"2021-07-13","cited_by_count":13},{"id":"1810.01835","title":"Human-Centered Autonomous Vehicle Systems: Principles of Effective Shared Autonomy","created":"2018-10-03","cited_by_count":7},{"id":"2111.11647","title":"Inducing Functions through Reinforcement Learning without Task Specification","created":"2021-11-23","cited_by_count":1}],"next_cursor":null}