{"list":"other","total":61,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1509.06461","title":"Deep Reinforcement Learning with Double Q-learning","created":"2015-09-22","cited_by_count":1745},{"id":"1911.08265","title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","created":"2019-11-19","cited_by_count":1353},{"id":"1705.05363","title":"Curiosity-driven Exploration by Self-supervised Prediction","created":"2017-05-15","cited_by_count":1194},{"id":"1511.05952","title":"Prioritized Experience Replay","created":"2015-11-18","cited_by_count":1099},{"id":"1710.02298","title":"Rainbow: Combining Improvements in Deep Reinforcement Learning","created":"2017-10-06","cited_by_count":786},{"id":"1511.06581","title":"Dueling Network Architectures for Deep Reinforcement Learning","created":"2015-11-20","cited_by_count":785},{"id":"1707.06887","title":"A Distributional Perspective on Reinforcement Learning","created":"2017-07-21","cited_by_count":765},{"id":"1710.06537","title":"Sim-to-Real Transfer of Robotic Control with Dynamics Randomization","created":"2017-10-18","cited_by_count":672},{"id":"1710.10044","title":"Distributional Reinforcement Learning with Quantile Regression","created":"2017-10-27","cited_by_count":474},{"id":"1611.05397","title":"Reinforcement Learning with Unsupervised Auxiliary Tasks","created":"2016-11-16","cited_by_count":404},{"id":"1812.02341","title":"Quantifying Generalization in Reinforcement Learning","created":"2018-12-06","cited_by_count":352},{"id":"1606.05312","title":"Successor Features for Transfer in Reinforcement Learning","created":"2016-06-16","cited_by_count":340},{"id":"1506.06579","title":"Understanding Neural Networks Through Deep Visualization","created":"2015-06-22","cited_by_count":334},{"id":"1812.02230","title":"Towards a Definition of Disentangled Representations","created":"2018-12-05","cited_by_count":296},{"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":"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":"2009.08319","title":"Decoupling Representation Learning from Reinforcement Learning","created":"2020-09-14","cited_by_count":269},{"id":"1706.10295","title":"Noisy Networks for Exploration","created":"2017-06-30","cited_by_count":266},{"id":"1807.04742","title":"Visual Reinforcement Learning with Imagined Goals","created":"2018-07-12","cited_by_count":251},{"id":"1702.03920","title":"Cognitive Mapping and Planning for Visual Navigation","created":"2017-02-13","cited_by_count":212},{"id":"1906.02736","title":"DeepMDP: Learning Continuous Latent Space Models for Representation Learning","created":"2019-06-06","cited_by_count":207},{"id":"1905.12588","title":"Meta-Learning Representations for Continual Learning","created":"2019-05-29","cited_by_count":189},{"id":"1507.08750","title":"Action-Conditional Video Prediction using Deep Networks in Atari Games","created":"2015-07-31","cited_by_count":172},{"id":"1509.06113","title":"Deep Spatial Autoencoders for Visuomotor Learning","created":"2015-09-21","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":"1711.00138","title":"Visualizing and Understanding Atari Agents","created":"2017-10-31","cited_by_count":141},{"id":"1910.03016","title":"Is a Good Representation Sufficient for Sample Efficient Reinforcement Learning?","created":"2019-10-07","cited_by_count":140},{"id":"1810.12282","title":"Assessing Generalization in Deep Reinforcement Learning","created":"2018-10-29","cited_by_count":133},{"id":"1802.04181","title":"State Representation Learning for Control: An Overview","created":"2018-02-12","cited_by_count":127},{"id":"1911.07676","title":"Learning with Good Feature Representations in Bandits and in RL with a Generative Model","created":"2019-11-18","cited_by_count":127},{"id":"2101.05265","title":"Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learning","created":"2021-01-13","cited_by_count":123},{"id":"1810.00123","title":"Generalization and Regularization in DQN","created":"2018-09-29","cited_by_count":118},{"id":"1707.03497","title":"Value Prediction Network","created":"2017-07-11","cited_by_count":117},{"id":"1807.11622","title":"Count-Based Exploration with the Successor Representation","created":"2018-07-31","cited_by_count":112},{"id":"1610.04286","title":"Sim-to-Real Robot Learning from Pixels with Progressive Nets","created":"2016-10-13","cited_by_count":94},{"id":"1612.08810","title":"The Predictron: End-To-End Learning and Planning","created":"2016-12-28","cited_by_count":93},{"id":"2102.05815","title":"Representation Matters: Offline Pretraining for Sequential Decision Making","created":"2021-02-11","cited_by_count":91},{"id":"1806.07937","title":"A Dissection of Overfitting and Generalization in Continuous Reinforcement Learning","created":"2018-06-20","cited_by_count":87},{"id":"1710.11089","title":"Eigenoption Discovery through the Deep Successor Representation","created":"2017-10-30","cited_by_count":86},{"id":"1810.04586","title":"The Laplacian in RL: Learning Representations with Efficient Approximations","created":"2018-10-10","cited_by_count":86},{"id":"1602.02658","title":"Graying the black box: Understanding DQNs","created":"2016-02-08","cited_by_count":68},{"id":"1703.02660","title":"Towards Generalization and Simplicity in Continuous Control","created":"2017-03-08","cited_by_count":68},{"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":"1807.09341","title":"Learning Plannable Representations with Causal InfoGAN","created":"2018-07-24","cited_by_count":57},{"id":"1901.11530","title":"A Geometric Perspective on Optimal Representations for Reinforcement Learning","created":"2019-01-31","cited_by_count":54},{"id":"1612.06018","title":"Self-Correcting Models for Model-Based Reinforcement Learning","created":"2016-12-19","cited_by_count":43},{"id":"1609.01995","title":"Unifying task specification in reinforcement learning","created":"2016-09-07","cited_by_count":41},{"id":"1809.04506","title":"Combined Reinforcement Learning via Abstract Representations","created":"2018-09-12","cited_by_count":37},{"id":"1811.06626","title":"The Utility of Sparse Representations for Control in Reinforcement Learning","created":"2018-11-15","cited_by_count":24},{"id":"1512.01563","title":"State of the Art Control of Atari Games Using Shallow Reinforcement Learning","created":"2015-12-04","cited_by_count":23},{"id":"2001.05411","title":"Lipschitz Lifelong Reinforcement Learning","created":"2020-01-15","cited_by_count":23},{"id":"2005.03648","title":"Plan2Vec: Unsupervised Representation Learning by Latent Plans","created":"2020-05-07","cited_by_count":21},{"id":"1806.01825","title":"The Effect of Planning Shape on Dyna-style Planning in High-dimensional State Spaces","created":"2018-06-05","cited_by_count":15},{"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":"1904.01318","title":"Finding and Visualizing Weaknesses of Deep Reinforcement Learning Agents","created":"2019-04-02","cited_by_count":15},{"id":"1904.01191","title":"Planning with Expectation Models","created":"2019-04-02","cited_by_count":12},{"id":"1912.08324","title":"Analysing Deep Reinforcement Learning Agents Trained with Domain Randomisation","created":"2019-12-18","cited_by_count":9},{"id":"2007.03807","title":"Towards a practical measure of interference for reinforcement learning","created":"2020-07-07","cited_by_count":6},{"id":"2002.10021","title":"How Transferable are the Representations Learned by Deep Q Agents?","created":"2020-02-24","cited_by_count":4}],"next_cursor":null}