{"list":"other","total":79,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"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":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"1502.05477","title":"Trust Region Policy Optimization","created":"2015-02-19","cited_by_count":2580},{"id":"1802.09477","title":"Addressing Function Approximation Error in Actor-Critic Methods","created":"2018-02-26","cited_by_count":2417},{"id":"1412.3555","title":"Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling","created":"2014-12-11","cited_by_count":2367},{"id":"1602.01783","title":"Asynchronous Methods for Deep Reinforcement Learning","created":"2016-02-04","cited_by_count":2258},{"id":"1703.06907","title":"Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World","created":"2017-03-20","cited_by_count":1498},{"id":"1811.04551","title":"Learning Latent Dynamics for Planning from Pixels","created":"2018-11-12","cited_by_count":1264},{"id":"1812.05905","title":"Soft Actor-Critic Algorithms and Applications","created":"2018-12-13","cited_by_count":1240},{"id":"1910.10897","title":"Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning","created":"2019-10-24","cited_by_count":1204},{"id":"1802.01561","title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures","created":"2018-02-05","cited_by_count":883},{"id":"1809.01999","title":"Recurrent World Models Facilitate Policy Evolution","created":"2018-09-04","cited_by_count":785},{"id":"1312.6120","title":"Exact solutions to the nonlinear dynamics of learning in deep linear neural networks","created":"2013-12-20","cited_by_count":763},{"id":"1611.02779","title":"RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning","created":"2016-11-09","cited_by_count":503},{"id":"1912.01588","title":"Leveraging Procedural Generation to Benchmark Reinforcement Learning","created":"2019-12-03","cited_by_count":483},{"id":"1507.06527","title":"Deep Recurrent Q-Learning for Partially Observable MDPs","created":"2015-07-23","cited_by_count":465},{"id":"1703.02702","title":"Robust Adversarial Reinforcement Learning","created":"2017-03-08","cited_by_count":451},{"id":"1611.05397","title":"Reinforcement Learning with Unsupervised Auxiliary Tasks","created":"2016-11-16","cited_by_count":404},{"id":"1903.08254","title":"Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables","created":"2019-03-19","cited_by_count":389},{"id":"1611.05763","title":"Learning to reinforcement learn","created":"2016-11-17","cited_by_count":377},{"id":"1609.05143","title":"Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning","created":"2016-09-16","cited_by_count":366},{"id":"1812.02341","title":"Quantifying Generalization in Reinforcement Learning","created":"2018-12-06","cited_by_count":352},{"id":"1702.02284","title":"Adversarial Attacks on Neural Network Policies","created":"2017-02-08","cited_by_count":320},{"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":"1910.06764","title":"Stabilizing Transformers for Reinforcement Learning","created":"2019-10-13","cited_by_count":270},{"id":"2003.08938","title":"Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations","created":"2020-03-19","cited_by_count":238},{"id":"1907.00953","title":"Stochastic Latent Actor-Critic: Deep Reinforcement Learning with a Latent Variable Model","created":"2019-07-01","cited_by_count":231},{"id":"1910.08348","title":"VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning","created":"2019-10-18","cited_by_count":217},{"id":"1905.10615","title":"Adversarial Policies: Attacking Deep Reinforcement Learning","created":"2019-05-25","cited_by_count":214},{"id":"1611.03673","title":"Learning to Navigate in Complex Environments","created":"2016-11-11","cited_by_count":198},{"id":"1804.06893","title":"A Study on Overfitting in Deep Reinforcement Learning","created":"2018-04-18","cited_by_count":174},{"id":"1901.09184","title":"Action Robust Reinforcement Learning and Applications in Continuous Control","created":"2019-01-26","cited_by_count":174},{"id":"1910.07207","title":"Soft Actor-Critic for Discrete Action Settings","created":"2019-10-16","cited_by_count":174},{"id":"1806.07857","title":"RUDDER: Return Decomposition for Delayed Rewards","created":"2018-06-20","cited_by_count":173},{"id":"1703.06748","title":"Tactics of Adversarial Attack on Deep Reinforcement Learning Agents","created":"2017-03-08","cited_by_count":166},{"id":"1712.03632","title":"Robust Deep Reinforcement Learning with Adversarial Attacks","created":"2017-12-11","cited_by_count":154},{"id":"2107.14171","title":"Tianshou: a Highly Modularized Deep Reinforcement Learning Library","created":"2021-07-29","cited_by_count":143},{"id":"1610.01283","title":"EPOpt: Learning Robust Neural Network Policies Using Model Ensembles","created":"2016-10-05","cited_by_count":138},{"id":"2101.08452","title":"Robust Reinforcement Learning on State Observations with Learned Optimal Adversary","created":"2021-01-21","cited_by_count":135},{"id":"1810.12282","title":"Assessing Generalization in Deep Reinforcement Learning","created":"2018-10-29","cited_by_count":133},{"id":"1806.02426","title":"Deep Variational Reinforcement Learning for POMDPs","created":"2018-06-06","cited_by_count":125},{"id":"1810.00123","title":"Generalization and Regularization in DQN","created":"2018-09-29","cited_by_count":118},{"id":"1910.05396","title":"Network Randomization: A Simple Technique for Generalization in Deep Reinforcement Learning","created":"2019-10-11","cited_by_count":104},{"id":"1910.12911","title":"Generalization in Reinforcement Learning with Selective Noise Injection and Information Bottleneck","created":"2019-10-28","cited_by_count":101},{"id":"1912.02975","title":"Observational Overfitting in Reinforcement Learning","created":"2019-12-06","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":"2102.10330","title":"Decoupling Value and Policy for Generalization in Reinforcement Learning","created":"2021-02-20","cited_by_count":82},{"id":"1806.10729","title":"Illuminating Generalization in Deep Reinforcement Learning through Procedural Level Generation","created":"2018-06-28","cited_by_count":81},{"id":"1912.02503","title":"Hindsight Credit Assignment","created":"2019-12-05","cited_by_count":79},{"id":"1512.04455","title":"Memory-based control with recurrent neural networks","created":"2015-12-14","cited_by_count":78},{"id":"1906.07516","title":"Robust Reinforcement Learning for Continuous Control with Model Misspecification","created":"2019-06-18","cited_by_count":78},{"id":"1905.06424","title":"Meta reinforcement learning as task inference","created":"2019-05-15","cited_by_count":77},{"id":"1703.02660","title":"Towards Generalization and Simplicity in Continuous Control","created":"2017-03-08","cited_by_count":68},{"id":"1906.09237","title":"Shaping Belief States with Generative Environment Models for RL","created":"2019-06-21","cited_by_count":66},{"id":"2011.09464","title":"Counterfactual Credit Assignment in Model-Free Reinforcement Learning","created":"2020-11-18","cited_by_count":64},{"id":"1910.00125","title":"Meta-Q-Learning","created":"2019-09-30","cited_by_count":62},{"id":"1605.09128","title":"Control of Memory, Active Perception, and Action in Minecraft","created":"2016-05-30","cited_by_count":61},{"id":"1902.06865","title":"Hyperbolic Discounting and Learning over Multiple Horizons","created":"2019-02-19","cited_by_count":60},{"id":"1803.00144","title":"Learning Longer-term Dependencies in RNNs with Auxiliary Losses","created":"2018-03-01","cited_by_count":58},{"id":"1810.06721","title":"Optimizing Agent Behavior over Long Time Scales by Transporting Value","created":"2018-10-15","cited_by_count":58},{"id":"1803.10760","title":"Unsupervised Predictive Memory in a Goal-Directed Agent","created":"2018-03-28","cited_by_count":55},{"id":"2005.05719","title":"Smooth Exploration for Robotic Reinforcement Learning","created":"2020-05-12","cited_by_count":54},{"id":"2102.12344","title":"Memory-based Deep Reinforcement Learning for POMDPs","created":"2021-02-24","cited_by_count":54},{"id":"2007.08433","title":"Meta-Gradient Reinforcement Learning with an Objective Discovered Online","created":"2020-07-16","cited_by_count":52},{"id":"1912.10703","title":"Variational Recurrent Models for Solving Partially Observable Control Tasks","created":"2019-12-23","cited_by_count":47},{"id":"1803.04848","title":"Soft-Robust Actor-Critic Policy-Gradient","created":"2018-03-11","cited_by_count":37},{"id":"2010.12718","title":"Learning Guidance Rewards with Trajectory-space Smoothing","created":"2020-10-23","cited_by_count":30},{"id":"1905.13420","title":"Sequence Modeling of Temporal Credit Assignment for Episodic Reinforcement Learning","created":"2019-05-31","cited_by_count":27},{"id":"2102.12425","title":"Synthetic Returns for Long-Term Credit Assignment","created":"2021-02-24","cited_by_count":27},{"id":"1805.09692","title":"Been There, Done That: Meta-Learning with Episodic Recall","created":"2018-05-24","cited_by_count":26},{"id":"1902.07015","title":"Investigating Generalisation in Continuous Deep Reinforcement Learning","created":"2019-02-19","cited_by_count":18},{"id":"1910.13038","title":"Learning to Predict Without Looking Ahead: World Models Without Forward Prediction","created":"2019-10-29","cited_by_count":15},{"id":"2107.04200","title":"Safe Exploration by Solving Early Terminated MDP","created":"2021-07-09","cited_by_count":15},{"id":"1808.09105","title":"SOLAR: Deep Structured Representations for Model-Based Reinforcement Learning","created":"2018-08-28","cited_by_count":14},{"id":"1902.05795","title":"Robust Reinforcement Learning in POMDPs with Incomplete and Noisy Observations","created":"2019-02-15","cited_by_count":10},{"id":"1802.08311","title":"Structured Control Nets for Deep Reinforcement Learning","created":"2018-02-22","cited_by_count":8}],"next_cursor":null}