{"list":"other","total":61,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1612.01474","title":"Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles","created":"2016-12-05","cited_by_count":3926},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"1912.01603","title":"Dream to Control: Learning Behaviors by Latent Imagination","created":"2019-12-03","cited_by_count":1653},{"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":"1811.04551","title":"Learning Latent Dynamics for Planning from Pixels","created":"2018-11-12","cited_by_count":1264},{"id":"1705.05363","title":"Curiosity-driven Exploration by Self-supervised Prediction","created":"2017-05-15","cited_by_count":1194},{"id":"1511.07289","title":"Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)","created":"2015-11-23","cited_by_count":1070},{"id":"1603.09382","title":"Deep Networks with Stochastic Depth","created":"2016-03-30","cited_by_count":979},{"id":"1805.12114","title":"Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models","created":"2018-05-30","cited_by_count":774},{"id":"1707.06887","title":"A Distributional Perspective on Reinforcement Learning","created":"2017-07-21","cited_by_count":765},{"id":"1606.01868","title":"Unifying Count-Based Exploration and Intrinsic Motivation","created":"2016-06-06","cited_by_count":639},{"id":"1902.02476","title":"A Simple Baseline for Bayesian Uncertainty in Deep Learning","created":"2019-02-07","cited_by_count":560},{"id":"1602.04621","title":"Deep Exploration via Bootstrapped DQN","created":"2016-02-15","cited_by_count":527},{"id":"1912.01588","title":"Leveraging Procedural Generation to Benchmark Reinforcement Learning","created":"2019-12-03","cited_by_count":483},{"id":"2002.08791","title":"Bayesian Deep Learning and a Probabilistic Perspective of Generalization","created":"2020-02-20","cited_by_count":480},{"id":"1611.05397","title":"Reinforcement Learning with Unsupervised Auxiliary Tasks","created":"2016-11-16","cited_by_count":404},{"id":"2006.12983","title":"dm_control: Software and Tasks for Continuous Control","created":"2020-06-22","cited_by_count":375},{"id":"2005.05960","title":"Planning to Explore via Self-Supervised World Models","created":"2020-05-12","cited_by_count":368},{"id":"1704.00109","title":"Snapshot Ensembles: Train 1, get M for free","created":"2017-04-01","cited_by_count":350},{"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":"1906.04161","title":"Self-Supervised Exploration via Disagreement","created":"2019-06-10","cited_by_count":265},{"id":"1606.02647","title":"Safe and Efficient Off-Policy Reinforcement Learning","created":"2016-06-08","cited_by_count":264},{"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":"1802.10592","title":"Model-Ensemble Trust-Region Policy Optimization","created":"2018-02-28","cited_by_count":219},{"id":"1806.03335","title":"Randomized Prior Functions for Deep Reinforcement Learning","created":"2018-06-08","cited_by_count":219},{"id":"1507.08750","title":"Action-Conditional Video Prediction using Deep Networks in Atari Games","created":"2015-07-31","cited_by_count":172},{"id":"2005.07186","title":"Efficient and Scalable Bayesian Neural Nets with Rank-1 Factors","created":"2020-05-14","cited_by_count":171},{"id":"1807.01675","title":"Sample-Efficient Reinforcement Learning with Stochastic Ensemble Value Expansion","created":"2018-07-04","cited_by_count":168},{"id":"1803.00101","title":"Model-Based Value Estimation for Efficient Model-Free Reinforcement Learning","created":"2018-02-28","cited_by_count":156},{"id":"1507.00814","title":"Incentivizing Exploration In Reinforcement Learning With Deep Predictive Models","created":"2015-07-03","cited_by_count":154},{"id":"2006.13570","title":"Hyperparameter Ensembles for Robustness and Uncertainty Quantification","created":"2020-06-24","cited_by_count":150},{"id":"2006.14911","title":"Can Autonomous Vehicles Identify, Recover From, and Adapt to Distribution Shifts?","created":"2020-06-26","cited_by_count":139},{"id":"2002.12292","title":"RIDE: Rewarding Impact-Driven Exploration for Procedurally-Generated Environments","created":"2020-02-27","cited_by_count":135},{"id":"1707.03497","title":"Value Prediction Network","created":"2017-07-11","cited_by_count":117},{"id":"1811.01848","title":"Plan Online, Learn Offline: Efficient Learning and Exploration via Model-Based Control","created":"2018-11-05","cited_by_count":113},{"id":"1611.01929","title":"Averaged-DQN: Variance Reduction and Stabilization for Deep Reinforcement Learning","created":"2016-11-07","cited_by_count":106},{"id":"1810.12162","title":"Model-Based Active Exploration","created":"2018-10-29","cited_by_count":105},{"id":"1810.05546","title":"Uncertainty in Neural Networks: Approximately Bayesian Ensembling","created":"2018-10-12","cited_by_count":94},{"id":"2011.03506","title":"The Value Equivalence Principle for Model-Based Reinforcement Learning","created":"2020-11-06","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":"1906.09237","title":"Shaping Belief States with Generative Environment Models for RL","created":"2019-06-21","cited_by_count":66},{"id":"1902.06865","title":"Hyperbolic Discounting and Learning over Multiple Horizons","created":"2019-02-19","cited_by_count":60},{"id":"2006.02243","title":"The Value-Improvement Path: Towards Better Representations for Reinforcement Learning","created":"2020-06-03","cited_by_count":60},{"id":"2103.04047","title":"Reinforcement Learning, Bit by Bit","created":"2021-03-06","cited_by_count":59},{"id":"2006.08437","title":"Depth Uncertainty in Neural Networks","created":"2020-06-15","cited_by_count":57},{"id":"2102.13089","title":"On The Effect of Auxiliary Tasks on Representation Dynamics","created":"2021-02-25","cited_by_count":57},{"id":"2104.06159","title":"Muesli: Combining Improvements in Policy Optimization","created":"2021-04-13","cited_by_count":53},{"id":"2106.04152","title":"PlayVirtual: Augmenting Cycle-Consistent Virtual Trajectories for Reinforcement Learning","created":"2021-06-08","cited_by_count":41},{"id":"1909.11583","title":"Off-Policy Actor-Critic with Shared Experience Replay","created":"2019-09-25","cited_by_count":39},{"id":"2106.03273","title":"Control-Oriented Model-Based Reinforcement Learning with Implicit Differentiation","created":"2021-06-06","cited_by_count":35},{"id":"2002.02693","title":"Ready Policy One: World Building Through Active Learning","created":"2020-02-07","cited_by_count":33},{"id":"2106.10316","title":"Proper Value Equivalence","created":"2021-06-18","cited_by_count":33},{"id":"1910.04142","title":"Imagined Value Gradients: Model-Based Policy Optimization with Transferable Latent Dynamics Models","created":"2019-10-09","cited_by_count":26},{"id":"2102.12560","title":"PsiPhi-Learning: Reinforcement Learning with Demonstrations using Successor Features and Inverse Temporal Difference Learning","created":"2021-02-24","cited_by_count":23},{"id":"1301.6690","title":"Model-Based Bayesian Exploration","created":"2013-01-23","cited_by_count":21},{"id":"2008.02430","title":"Contrastive Variational Reinforcement Learning for Complex Observations","created":"2020-08-06","cited_by_count":15},{"id":"2010.02255","title":"Temporal Difference Uncertainties as a Signal for Exploration","created":"2020-10-05","cited_by_count":15},{"id":"1907.01475","title":"Generalizing from a few environments in safety-critical reinforcement learning","created":"2019-07-02","cited_by_count":8},{"id":"2110.12840","title":"Self-Consistent Models and Values","created":"2021-10-25","cited_by_count":7},{"id":"2002.08329","title":"Value-driven Hindsight Modelling","created":"2020-02-19","cited_by_count":6}],"next_cursor":null}