{"list":"other","total":53,"rows":[{"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":"1509.02971","title":"Continuous control with deep reinforcement learning","created":"2015-09-09","cited_by_count":3407},{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920},{"id":"2006.04779","title":"Conservative Q-Learning for Offline Reinforcement Learning","created":"2020-06-08","cited_by_count":1809},{"id":"1509.06461","title":"Deep Reinforcement Learning with Double Q-learning","created":"2015-09-22","cited_by_count":1745},{"id":"1606.03476","title":"Generative Adversarial Imitation Learning","created":"2016-06-10","cited_by_count":1597},{"id":"1812.02900","title":"Off-Policy Deep Reinforcement Learning without Exploration","created":"2018-12-07","cited_by_count":1241},{"id":"1705.05363","title":"Curiosity-driven Exploration by Self-supervised Prediction","created":"2017-05-15","cited_by_count":1194},{"id":"1612.03975","title":"ConceptNet 5.5: An Open Multilingual Graph of General Knowledge","created":"2016-12-12","cited_by_count":1067},{"id":"1810.12894","title":"Exploration by Random Network Distillation","created":"2018-10-30","cited_by_count":993},{"id":"2004.05439","title":"Meta-Learning in Neural Networks: A Survey","created":"2020-04-11","cited_by_count":950},{"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":"1603.00448","title":"Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization","created":"2016-03-01","cited_by_count":406},{"id":"2102.08363","title":"COMBO: Conservative Offline Model-Based Policy Optimization","created":"2021-02-16","cited_by_count":370},{"id":"2005.05960","title":"Planning to Explore via Self-Supervised World Models","created":"2020-05-12","cited_by_count":368},{"id":"1703.01161","title":"FeUdal Networks for Hierarchical Reinforcement Learning","created":"2017-03-03","cited_by_count":337},{"id":"1903.01973","title":"Learning Latent Plans from Play","created":"2019-03-05","cited_by_count":316},{"id":"1610.00696","title":"Deep Visual Foresight for Planning Robot Motion","created":"2016-10-03","cited_by_count":285},{"id":"2012.13490","title":"Towards Continual Reinforcement Learning: A Review and Perspectives","created":"2020-12-25","cited_by_count":274},{"id":"1711.02827","title":"Inverse Reward Design","created":"2017-11-08","cited_by_count":249},{"id":"2002.06038","title":"Never Give Up: Learning Directed Exploration Strategies","created":"2020-02-14","cited_by_count":212},{"id":"2106.12142","title":"IQ-Learn: Inverse soft-Q Learning for Imitation","created":"2021-06-23","cited_by_count":193},{"id":"2002.02794","title":"Reward-Free Exploration for Reinforcement Learning","created":"2020-02-07","cited_by_count":177},{"id":"2110.11328","title":"A Fine-Grained Analysis on Distribution Shift","created":"2021-10-21","cited_by_count":171},{"id":"1611.03852","title":"A Connection between Generative Adversarial Networks, Inverse Reinforcement Learning, and Energy-Based Models","created":"2016-11-11","cited_by_count":168},{"id":"2201.08299","title":"Goal-Conditioned Reinforcement Learning: Problems and Solutions","created":"2022-01-20","cited_by_count":158},{"id":"1606.07419","title":"Learning to Poke by Poking: Experiential Learning of Intuitive Physics","created":"2016-06-23","cited_by_count":154},{"id":"2110.09514","title":"Discovering and Achieving Goals via World Models","created":"2021-10-18","cited_by_count":131},{"id":"1901.09387","title":"Imitation Learning from Imperfect Demonstration","created":"2019-01-27","cited_by_count":114},{"id":"1805.07914","title":"Imitating Latent Policies from Observation","created":"2018-05-21","cited_by_count":101},{"id":"1905.13566","title":"Recent Advances in Imitation Learning from Observation","created":"2019-05-30","cited_by_count":93},{"id":"2008.06043","title":"Offline Meta-Reinforcement Learning with Advantage Weighting","created":"2020-08-13","cited_by_count":93},{"id":"2006.12122","title":"Learning with AMIGo: Adversarially Motivated Intrinsic Goals","created":"2020-06-22","cited_by_count":88},{"id":"2002.09571","title":"Learning to Continually Learn","created":"2020-02-21","cited_by_count":84},{"id":"1707.02201","title":"Learning human behaviors from motion capture by adversarial imitation","created":"2017-07-07","cited_by_count":77},{"id":"2109.00157","title":"A Survey of Exploration Methods in Reinforcement Learning","created":"2021-09-01","cited_by_count":73},{"id":"2106.12177","title":"Imitation Learning: Progress, Taxonomies and Challenges","created":"2021-06-23","cited_by_count":58},{"id":"2007.07170","title":"Goal-Aware Prediction: Learning to Model What Matters","created":"2020-07-14","cited_by_count":45},{"id":"2102.05824","title":"Reproducibility Report: La-MAML: Look-ahead Meta Learning for Continual Learning","created":"2021-02-11","cited_by_count":42},{"id":"2003.12045","title":"Use the Force, Luke! Learning to Predict Physical Forces by Simulating Effects","created":"2020-03-26","cited_by_count":40},{"id":"1805.09461","title":"Deep Reinforcement Learning For Sequence to Sequence Models","created":"2018-05-24","cited_by_count":39},{"id":"2111.13119","title":"Interesting Object, Curious Agent: Learning Task-Agnostic Exploration","created":"2021-11-25","cited_by_count":38},{"id":"2006.09497","title":"Task-agnostic Exploration in Reinforcement Learning","created":"2020-06-16","cited_by_count":37},{"id":"2007.11808","title":"Deep Reinforcement Learning based Automatic Exploration for Navigation in Unknown Environment","created":"2020-07-23","cited_by_count":34},{"id":"2006.08875","title":"Model-based Adversarial Meta-Reinforcement Learning","created":"2020-06-16","cited_by_count":33},{"id":"2103.05910","title":"Learning from Imperfect Demonstrations from Agents with Varying Dynamics","created":"2021-03-10","cited_by_count":27},{"id":"1912.11809","title":"Variational Metric Scaling for Metric-Based Meta-Learning","created":"2019-12-26","cited_by_count":17},{"id":"2205.14495","title":"Task-Agnostic Continual Reinforcement Learning: Gaining Insights and Overcoming Challenges","created":"2022-05-28","cited_by_count":11},{"id":"2105.04556","title":"TANGO: Commonsense Generalization in Predicting Tool Interactions for Mobile Manipulators","created":"2021-05-05","cited_by_count":6},{"id":"2111.09884","title":"Assisted Robust Reward Design","created":"2021-11-18","cited_by_count":5},{"id":"2206.11733","title":"Walk the Random Walk: Learning to Discover and Reach Goals Without Supervision","created":"2022-06-23","cited_by_count":3}],"next_cursor":null}