{"list":"other","total":48,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"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":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"id":"1509.06461","title":"Deep Reinforcement Learning with Double Q-learning","created":"2015-09-22","cited_by_count":1745},{"id":"1511.05952","title":"Prioritized Experience Replay","created":"2015-11-18","cited_by_count":1099},{"id":"1702.03118","title":"Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning","created":"2017-02-10","cited_by_count":950},{"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":"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":"1709.06560","title":"Deep Reinforcement Learning that Matters","created":"2017-09-19","cited_by_count":754},{"id":"1612.08083","title":"Language Modeling with Gated Convolutional Networks","created":"2016-12-23","cited_by_count":702},{"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":"1903.00374","title":"Model-Based Reinforcement Learning for Atari","created":"2019-03-01","cited_by_count":502},{"id":"1604.06778","title":"Benchmarking Deep Reinforcement Learning for Continuous Control","created":"2016-04-22","cited_by_count":371},{"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":"1706.10295","title":"Noisy Networks for Exploration","created":"2017-06-30","cited_by_count":266},{"id":"2005.12729","title":"Implementation Matters in Deep Policy Gradients: A Case Study on PPO and TRPO","created":"2020-05-25","cited_by_count":186},{"id":"2302.12902","title":"The Dormant Neuron Phenomenon in Deep Reinforcement Learning","created":"2023-02-24","cited_by_count":174},{"id":"2305.19452","title":"Bigger, Better, Faster: Human-level Atari with human-level efficiency","created":"2023-05-30","cited_by_count":147},{"id":"1812.06110","title":"Dopamine: A Research Framework for Deep Reinforcement Learning","created":"2018-12-14","cited_by_count":122},{"id":"1906.05243","title":"When to use parametric models in reinforcement learning?","created":"2019-06-12","cited_by_count":118},{"id":"2007.09055","title":"Hyperparameter Selection for Offline Reinforcement Learning","created":"2020-07-17","cited_by_count":114},{"id":"1611.01929","title":"Averaged-DQN: Variance Reduction and Stabilization for Deep Reinforcement Learning","created":"2016-11-07","cited_by_count":106},{"id":"2210.05639","title":"Discovered Policy Optimisation","created":"2022-10-11","cited_by_count":104},{"id":"1708.04133","title":"Reproducibility of Benchmarked Deep Reinforcement Learning Tasks for Continuous Control","created":"2017-08-10","cited_by_count":93},{"id":"2011.14826","title":"Revisiting Rainbow: Promoting more Insightful and Inclusive Deep Reinforcement Learning Research","created":"2020-11-20","cited_by_count":78},{"id":"2201.03916","title":"Automated Reinforcement Learning (AutoRL): A Survey and Open Problems","created":"2022-01-11","cited_by_count":70},{"id":"2105.05246","title":"Spectral Normalisation for Deep Reinforcement Learning: an Optimisation Perspective","created":"2021-05-11","cited_by_count":65},{"id":"2206.10369","title":"The State of Sparse Training in Deep Reinforcement Learning","created":"2022-06-17","cited_by_count":61},{"id":"2306.01324","title":"Hyperparameters in Reinforcement Learning and How To Tune Them","created":"2023-06-02","cited_by_count":59},{"id":"1912.05663","title":"Measuring the Reliability of Reinforcement Learning Algorithms","created":"2019-12-10","cited_by_count":51},{"id":"2110.04135","title":"Revisiting Design Choices in Offline Model-Based Reinforcement Learning","created":"2021-10-08","cited_by_count":50},{"id":"2110.14020","title":"The Difficulty of Passive Learning in Deep Reinforcement Learning","created":"2021-10-26","cited_by_count":50},{"id":"2101.03958","title":"Evolving Reinforcement Learning Algorithms","created":"2021-01-08","cited_by_count":49},{"id":"1901.09455","title":"Off-Policy Deep Reinforcement Learning by Bootstrapping the Covariate Shift","created":"2019-01-27","cited_by_count":47},{"id":"2007.02040","title":"Discount Factor as a Regularizer in Reinforcement Learning","created":"2020-07-04","cited_by_count":45},{"id":"2304.12567","title":"Proto-Value Networks: Scaling Representation Learning with Auxiliary Tasks","created":"2023-04-25","cited_by_count":42},{"id":"1906.02341","title":"How to Initialize your Network? Robust Initialization for WeightNorm & ResNets","created":"2019-06-05","cited_by_count":36},{"id":"2310.03882","title":"Small batch deep reinforcement learning","created":"2023-10-05","cited_by_count":36},{"id":"1512.02011","title":"How to Discount Deep Reinforcement Learning: Towards New Dynamic Strategies","created":"2015-12-07","cited_by_count":27},{"id":"1907.02908","title":"On Inductive Biases in Deep Reinforcement Learning","created":"2019-07-05","cited_by_count":24},{"id":"2105.12034","title":"Hyperparameter Selection for Imitation Learning","created":"2021-05-25","cited_by_count":17},{"id":"1906.00572","title":"Using a Logarithmic Mapping to Enable Lower Discount Factors in Reinforcement Learning","created":"2019-06-03","cited_by_count":16},{"id":"2010.09931","title":"Smooth activations and reproducibility in deep networks","created":"2020-10-20","cited_by_count":16}],"next_cursor":null}