{"list":"other","total":53,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1506.02142","title":"Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning","created":"2015-06-06","cited_by_count":4448},{"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":"1602.01783","title":"Asynchronous Methods for Deep Reinforcement Learning","created":"2016-02-04","cited_by_count":2258},{"id":"1606.01540","title":"OpenAI Gym","created":"2016-06-05","cited_by_count":1736},{"id":"1906.02530","title":"Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift","created":"2019-06-06","cited_by_count":1287},{"id":"2011.06225","title":"A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges","created":"2020-11-12","cited_by_count":819},{"id":"2110.11334","title":"Generalized Out-of-Distribution Detection: A Survey","created":"2021-10-21","cited_by_count":802},{"id":"1707.06887","title":"A Distributional Perspective on Reinforcement Learning","created":"2017-07-21","cited_by_count":765},{"id":"1809.11165","title":"GPyTorch: Blackbox Matrix-Matrix Gaussian Process Inference with GPU Acceleration","created":"2018-09-28","cited_by_count":609},{"id":"1902.02476","title":"A Simple Baseline for Bayesian Uncertainty in Deep Learning","created":"2019-02-07","cited_by_count":560},{"id":"1802.10501","title":"Predictive Uncertainty Estimation via Prior Networks","created":"2018-02-28","cited_by_count":557},{"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":"2108.13624","title":"Towards Out-Of-Distribution Generalization: A Survey","created":"2021-08-31","cited_by_count":436},{"id":"2002.06715","title":"BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learning","created":"2020-02-17","cited_by_count":371},{"id":"1806.06923","title":"Implicit Quantile Networks for Distributional Reinforcement Learning","created":"2018-06-14","cited_by_count":369},{"id":"1910.02600","title":"Deep Evidential Regression","created":"2019-10-07","cited_by_count":355},{"id":"1812.02341","title":"Quantifying Generalization in Reinforcement Learning","created":"2018-12-06","cited_by_count":352},{"id":"1512.01629","title":"Risk-Constrained Reinforcement Learning with Percentile Risk Criteria","created":"2015-12-05","cited_by_count":337},{"id":"1812.05720","title":"Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem","created":"2018-12-13","cited_by_count":323},{"id":"1901.04592","title":"Interpretable machine learning: definitions, methods, and applications","created":"2019-01-14","cited_by_count":305},{"id":"1611.01491","title":"Understanding Deep Neural Networks with Rectified Linear Units","created":"2016-11-04","cited_by_count":257},{"id":"2002.10118","title":"Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networks","created":"2020-02-24","cited_by_count":231},{"id":"1806.03335","title":"Randomized Prior Functions for Deep Reinforcement Learning","created":"2018-06-08","cited_by_count":219},{"id":"1611.01224","title":"Sample Efficient Actor-Critic with Experience Replay","created":"2016-11-03","cited_by_count":188},{"id":"1403.5341","title":"An Information-Theoretic Analysis of Thompson Sampling","created":"2014-03-21","cited_by_count":178},{"id":"1807.01675","title":"Sample-Efficient Reinforcement Learning with Stochastic Ensemble Value Expansion","created":"2018-07-04","cited_by_count":168},{"id":"2006.09239","title":"Posterior Network: Uncertainty Estimation without OOD Samples via Density-Based Pseudo-Counts","created":"2020-06-16","cited_by_count":164},{"id":"2006.13570","title":"Hyperparameter Ensembles for Robustness and Uncertainty Quantification","created":"2020-06-24","cited_by_count":150},{"id":"1810.12282","title":"Assessing Generalization in Deep Reinforcement Learning","created":"2018-10-29","cited_by_count":133},{"id":"1908.03568","title":"Behaviour Suite for Reinforcement Learning","created":"2019-08-09","cited_by_count":132},{"id":"2107.06277","title":"Why Generalization in RL is Difficult: Epistemic POMDPs and Implicit Partial Observability","created":"2021-07-13","cited_by_count":109},{"id":"2107.07455","title":"Shifts: A Dataset of Real Distributional Shift Across Multiple Large-Scale Tasks","created":"2021-07-15","cited_by_count":101},{"id":"1702.01182","title":"Uncertainty-Aware Reinforcement Learning for Collision Avoidance","created":"2017-02-03","cited_by_count":88},{"id":"2102.11409","title":"On Feature Collapse and Deep Kernel Learning for Single Forward Pass Uncertainty","created":"2021-02-22","cited_by_count":87},{"id":"1611.02247","title":"Q-Prop: Sample-Efficient Policy Gradient with An Off-Policy Critic","created":"2016-11-07","cited_by_count":81},{"id":"2110.14012","title":"Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classification","created":"2021-10-26","cited_by_count":80},{"id":"1810.08700","title":"Safe Reinforcement Learning with Model Uncertainty Estimates","created":"2018-10-19","cited_by_count":72},{"id":"1905.09638","title":"Estimating Risk and Uncertainty in Deep Reinforcement Learning","created":"2019-05-23","cited_by_count":70},{"id":"1909.12180","title":"Towards neural networks that provably know when they don't know","created":"2019-09-26","cited_by_count":69},{"id":"2006.13827","title":"Risk-Sensitive Reinforcement Learning: Near-Optimal Risk-Sample Tradeoff in Regret","created":"2020-06-22","cited_by_count":58},{"id":"1812.07544","title":"Information-Directed Exploration for Deep Reinforcement Learning","created":"2018-12-18","cited_by_count":52},{"id":"2010.14986","title":"Evaluating Robustness of Predictive Uncertainty Estimation: Are Dirichlet-based Models Reliable?","created":"2020-10-28","cited_by_count":39},{"id":"2011.01413","title":"Out-of-Distribution Detection for Automotive Perception","created":"2020-11-03","cited_by_count":37},{"id":"2006.11590","title":"Regression Prior Networks","created":"2020-06-20","cited_by_count":28},{"id":"1911.05503","title":"Uncertainty on Asynchronous Time Event Prediction","created":"2019-11-13","cited_by_count":27},{"id":"1906.06273","title":"Epistemic Risk-Sensitive Reinforcement Learning","created":"2019-06-14","cited_by_count":17},{"id":"2107.04982","title":"Out-of-Distribution Dynamics Detection: RL-Relevant Benchmarks and Results","created":"2021-07-11","cited_by_count":14},{"id":"2112.02694","title":"Benchmark for Out-of-Distribution Detection in Deep Reinforcement Learning","created":"2021-12-05","cited_by_count":9}],"next_cursor":null}