{"list":"other","total":95,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"1703.04977","title":"What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?","created":"2017-03-15","cited_by_count":2352},{"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":"2010.02193","title":"Mastering Atari with Discrete World Models","created":"2020-10-05","cited_by_count":1007},{"id":"1810.12894","title":"Exploration by Random Network Distillation","created":"2018-10-30","cited_by_count":993},{"id":"1802.01561","title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures","created":"2018-02-05","cited_by_count":883},{"id":"2108.13264","title":"Deep Reinforcement Learning at the Edge of the Statistical Precipice","created":"2021-08-30","cited_by_count":807},{"id":"1710.02298","title":"Rainbow: Combining Improvements in Deep Reinforcement Learning","created":"2017-10-06","cited_by_count":786},{"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":"2004.13649","title":"Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels","created":"2020-04-28","cited_by_count":585},{"id":"1602.04621","title":"Deep Exploration via Bootstrapped DQN","created":"2016-02-15","cited_by_count":527},{"id":"1703.05449","title":"Minimax Regret Bounds for Reinforcement Learning","created":"2017-03-16","cited_by_count":503},{"id":"1912.01588","title":"Leveraging Procedural Generation to Benchmark Reinforcement Learning","created":"2019-12-03","cited_by_count":483},{"id":"1710.10044","title":"Distributional Reinforcement Learning with Quantile Regression","created":"2017-10-27","cited_by_count":474},{"id":"2004.14990","title":"Reinforcement Learning with Augmented Data","created":"2020-04-30","cited_by_count":468},{"id":"1912.02757","title":"Deep Ensembles: A Loss Landscape Perspective","created":"2019-12-05","cited_by_count":443},{"id":"2006.10742","title":"Learning Invariant Representations for Reinforcement Learning without Reconstruction","created":"2020-06-18","cited_by_count":436},{"id":"2107.09645","title":"Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning","created":"2021-07-20","cited_by_count":372},{"id":"1812.02341","title":"Quantifying Generalization in Reinforcement Learning","created":"2018-12-06","cited_by_count":352},{"id":"2003.13350","title":"Agent57: Outperforming the Atari Human Benchmark","created":"2020-03-30","cited_by_count":303},{"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":"1803.00933","title":"Distributed Prioritized Experience Replay","created":"2018-03-02","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":"2205.07802","title":"The Primacy Bias in Deep Reinforcement Learning","created":"2022-05-16","cited_by_count":247},{"id":"1306.0940","title":"(More) Efficient Reinforcement Learning via Posterior Sampling","created":"2013-06-04","cited_by_count":233},{"id":"1502.02259","title":"Contextual Markov Decision Processes","created":"2015-02-08","cited_by_count":220},{"id":"2109.06780","title":"Benchmarking the Spectrum of Agent Capabilities","created":"2021-09-14","cited_by_count":200},{"id":"2006.13760","title":"The NetHack Learning Environment","created":"2020-06-24","cited_by_count":198},{"id":"2010.03934","title":"Prioritized Level Replay","created":"2020-10-08","cited_by_count":198},{"id":"2107.12808","title":"Open-Ended Learning Leads to Generally Capable Agents","created":"2021-07-27","cited_by_count":182},{"id":"1804.06893","title":"A Study on Overfitting in Deep Reinforcement Learning","created":"2018-04-18","cited_by_count":174},{"id":"1903.03698","title":"Skew-Fit: State-Covering Self-Supervised Reinforcement Learning","created":"2019-03-08","cited_by_count":174},{"id":"2203.01302","title":"Evolving Curricula with Regret-Based Environment Design","created":"2022-03-02","cited_by_count":173},{"id":"2007.04938","title":"SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learning","created":"2020-07-09","cited_by_count":152},{"id":"2011.13389","title":"Generalization in Reinforcement Learning by Soft Data Augmentation","created":"2020-11-26","cited_by_count":137},{"id":"2002.12292","title":"RIDE: Rewarding Impact-Driven Exploration for Procedurally-Generated Environments","created":"2020-02-27","cited_by_count":135},{"id":"1810.12282","title":"Assessing Generalization in Deep Reinforcement Learning","created":"2018-10-29","cited_by_count":133},{"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":"2103.07945","title":"Learning One Representation to Optimize All Rewards","created":"2021-03-14","cited_by_count":115},{"id":"1402.0635","title":"Generalization and Exploration via Randomized Value Functions","created":"2014-02-04","cited_by_count":112},{"id":"1807.11622","title":"Count-Based Exploration with the Successor Representation","created":"2018-07-31","cited_by_count":112},{"id":"2110.02439","title":"Replay-Guided Adversarial Environment Design","created":"2021-10-06","cited_by_count":111},{"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":"1510.08906","title":"Sample Complexity of Episodic Fixed-Horizon Reinforcement Learning","created":"2015-10-29","cited_by_count":106},{"id":"2003.06016","title":"Invariant Causal Prediction for Block MDPs","created":"2020-03-12","cited_by_count":105},{"id":"2107.00644","title":"Stabilizing Deep Q-Learning with ConvNets and Vision Transformers under Data Augmentation","created":"2021-07-01","cited_by_count":105},{"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":"2006.03041","title":"Sample Complexity of Asynchronous Q-Learning: Sharper Analysis and Variance Reduction","created":"2020-06-04","cited_by_count":95},{"id":"1810.05546","title":"Uncertainty in Neural Networks: Approximately Bayesian Ensembling","created":"2018-10-12","cited_by_count":94},{"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":"1709.05380","title":"The Uncertainty Bellman Equation and Exploration","created":"2017-09-15","cited_by_count":82},{"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":"2010.10814","title":"Improving Generalization in Reinforcement Learning with Mixture Regularization","created":"2020-10-21","cited_by_count":81},{"id":"2006.07217","title":"Deep Reinforcement and InfoMax Learning","created":"2020-06-12","cited_by_count":79},{"id":"2010.14484","title":"One Solution is Not All You Need: Few-Shot Extrapolation via Structured MaxEnt RL","created":"2020-10-27","cited_by_count":79},{"id":"2006.12862","title":"Automatic Data Augmentation for Generalization in Deep Reinforcement Learning","created":"2020-06-23","cited_by_count":71},{"id":"1905.09638","title":"Estimating Risk and Uncertainty in Deep Reinforcement Learning","created":"2019-05-23","cited_by_count":70},{"id":"1703.02660","title":"Towards Generalization and Simplicity in Continuous Control","created":"2017-03-08","cited_by_count":68},{"id":"1905.06125","title":"Distributional Reinforcement Learning for Efficient Exploration","created":"2019-05-13","cited_by_count":60},{"id":"1804.03720","title":"Gotta Learn Fast: A New Benchmark for Generalization in RL","created":"2018-04-10","cited_by_count":59},{"id":"2008.02790","title":"Decoupling Exploration and Exploitation for Meta-Reinforcement Learning without Sacrifices","created":"2020-08-06","cited_by_count":59},{"id":"2106.15612","title":"Learning Task Informed Abstractions","created":"2021-06-29","cited_by_count":58},{"id":"1902.01378","title":"Obstacle Tower: A Generalization Challenge in Vision, Control, and Planning","created":"2019-02-04","cited_by_count":54},{"id":"2102.04376","title":"Adversarially Guided Actor-Critic","created":"2021-02-08","cited_by_count":47},{"id":"2003.06350","title":"Interference and Generalization in Temporal Difference Learning","created":"2020-03-13","cited_by_count":42},{"id":"1507.00300","title":"Bootstrapped Thompson Sampling and Deep Exploration","created":"2015-07-01","cited_by_count":40},{"id":"2006.01096","title":"Invariant Policy Optimization: Towards Stronger Generalization in Reinforcement Learning","created":"2020-06-01","cited_by_count":37},{"id":"2006.09497","title":"Task-agnostic Exploration in Reinforcement Learning","created":"2020-06-16","cited_by_count":37},{"id":"2109.11052","title":"On Bonus-Based Exploration Methods in the Arcade Learning Environment","created":"2021-09-22","cited_by_count":37},{"id":"1912.03517","title":"No-Regret Exploration in Goal-Oriented Reinforcement Learning","created":"2019-12-07","cited_by_count":34},{"id":"2102.13268","title":"DRIBO: Robust Deep Reinforcement Learning via Multi-View Information Bottleneck","created":"2021-02-26","cited_by_count":31},{"id":"2111.01587","title":"Procedural Generalization by Planning with Self-Supervised World Models","created":"2021-11-02","cited_by_count":31},{"id":"2101.08152","title":"Rank the Episodes: A Simple Approach for Exploration in Procedurally-Generated Environments","created":"2021-01-20","cited_by_count":28},{"id":"2206.01558","title":"Disentangling Epistemic and Aleatoric Uncertainty in Reinforcement Learning","created":"2022-06-03","cited_by_count":27},{"id":"2001.09908","title":"Rotation, Translation, and Cropping for Zero-Shot Generalization","created":"2020-01-27","cited_by_count":24},{"id":"2103.15332","title":"Measuring Sample Efficiency and Generalization in Reinforcement Learning Benchmarks: NeurIPS 2020 Procgen Benchmark","created":"2021-03-29","cited_by_count":23},{"id":"2010.06740","title":"Measuring Visual Generalization in Continuous Control from Pixels","created":"2020-10-13","cited_by_count":21},{"id":"2101.00300","title":"When Is Generalizable Reinforcement Learning Tractable?","created":"2021-01-01","cited_by_count":20},{"id":"1703.08667","title":"Exploration--Exploitation in MDPs with Options","created":"2017-03-25","cited_by_count":19},{"id":"2011.01089","title":"Instance based Generalization in Reinforcement Learning","created":"2020-11-02","cited_by_count":17},{"id":"2111.14629","title":"Improving Zero-shot Generalization in Offline Reinforcement Learning using Generalized Similarity Functions","created":"2021-11-29","cited_by_count":17},{"id":"2206.02126","title":"Learning Dynamics and Generalization in Reinforcement Learning","created":"2022-06-05","cited_by_count":14},{"id":"2209.07670","title":"Reducing Variance in Temporal-Difference Value Estimation via Ensemble of Deep Networks","created":"2022-09-16","cited_by_count":13},{"id":"2004.12399","title":"Reinforcement Learning Generalization with Surprise Minimization","created":"2020-04-26","cited_by_count":10},{"id":"2006.03465","title":"Visual Transfer for Reinforcement Learning via Wasserstein Domain Confusion","created":"2020-06-04","cited_by_count":5},{"id":"2102.08581","title":"Efficient Scheduling of Data Augmentation for Deep Reinforcement Learning","created":"2021-02-17","cited_by_count":3}],"next_cursor":null}