{"list":"other","total":75,"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":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"id":"1509.02971","title":"Continuous control with deep reinforcement learning","created":"2015-09-09","cited_by_count":3407},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"1502.05477","title":"Trust Region Policy Optimization","created":"2015-02-19","cited_by_count":2580},{"id":"1912.04838","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","created":"2019-12-10","cited_by_count":2451},{"id":"1802.09477","title":"Addressing Function Approximation Error in Actor-Critic Methods","created":"2018-02-26","cited_by_count":2417},{"id":"1704.00028","title":"Improved Training of Wasserstein GANs","created":"2017-03-31","cited_by_count":2235},{"id":"1711.05101","title":"Decoupled Weight Decay Regularization","created":"2017-11-14","cited_by_count":1831},{"id":"1509.06461","title":"Deep Reinforcement Learning with Double Q-learning","created":"2015-09-22","cited_by_count":1745},{"id":"1802.05957","title":"Spectral Normalization for Generative Adversarial Networks","created":"2018-02-16","cited_by_count":1636},{"id":"1606.03476","title":"Generative Adversarial Imitation Learning","created":"2016-06-10","cited_by_count":1597},{"id":"1609.04836","title":"On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima","created":"2016-09-15","cited_by_count":1352},{"id":"1712.09913","title":"Visualizing the Loss Landscape of Neural Nets","created":"2017-12-28","cited_by_count":1130},{"id":"1505.05192","title":"Unsupervised Visual Representation Learning by Context Prediction","created":"2015-05-19","cited_by_count":1066},{"id":"1810.12894","title":"Exploration by Random Network Distillation","created":"2018-10-30","cited_by_count":993},{"id":"1906.02629","title":"When Does Label Smoothing Help?","created":"2019-06-06","cited_by_count":988},{"id":"1710.02298","title":"Rainbow: Combining Improvements in Deep Reinforcement Learning","created":"2017-10-06","cited_by_count":786},{"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":"1910.07113","title":"Solving Rubik's Cube with a Robot Hand","created":"2019-10-16","cited_by_count":734},{"id":"1801.04406","title":"Which Training Methods for GANs do actually Converge?","created":"2018-01-13","cited_by_count":679},{"id":"1701.07875","title":"Wasserstein GAN","created":"2017-01-26","cited_by_count":639},{"id":"1509.01240","title":"Train faster, generalize better: Stability of stochastic gradient descent","created":"2015-09-03","cited_by_count":552},{"id":"1703.04933","title":"Sharp Minima Can Generalize For Deep Nets","created":"2017-03-15","cited_by_count":466},{"id":"1701.04862","title":"Towards Principled Methods for Training Generative Adversarial Networks","created":"2017-01-17","cited_by_count":464},{"id":"1511.06295","title":"Policy Distillation","created":"2015-11-19","cited_by_count":440},{"id":"1611.05397","title":"Reinforcement Learning with Unsupervised Auxiliary Tasks","created":"2016-11-16","cited_by_count":404},{"id":"1804.04368","title":"Regularisation of Neural Networks by Enforcing Lipschitz Continuity","created":"2018-04-12","cited_by_count":314},{"id":"1704.08847","title":"Parseval Networks: Improving Robustness to Adversarial Examples","created":"2017-04-28","cited_by_count":293},{"id":"1701.00160","title":"NIPS 2016 Tutorial: Generative Adversarial Networks","created":"2016-12-31","cited_by_count":285},{"id":"1711.10337","title":"Are GANs Created Equal? A Large-Scale Study","created":"2017-11-28","cited_by_count":267},{"id":"1706.10295","title":"Noisy Networks for Exploration","created":"2017-06-30","cited_by_count":266},{"id":"1703.07326","title":"One-Shot Imitation Learning","created":"2017-03-21","cited_by_count":233},{"id":"1611.03673","title":"Learning to Navigate in Complex Environments","created":"2016-11-11","cited_by_count":198},{"id":"1611.01224","title":"Sample Efficient Actor-Critic with Experience Replay","created":"2016-11-03","cited_by_count":188},{"id":"1812.02648","title":"Deep Reinforcement Learning and the Deadly Triad","created":"2018-12-06","cited_by_count":174},{"id":"1706.01905","title":"Parameter Space Noise for Exploration","created":"2017-06-06","cited_by_count":161},{"id":"1609.03126","title":"Energy-based Generative Adversarial Network","created":"2016-09-11","cited_by_count":119},{"id":"1705.09367","title":"Stabilizing Training of Generative Adversarial Networks through Regularization","created":"2017-05-25","cited_by_count":118},{"id":"2002.08550","title":"Learning to Walk in the Real World with Minimal Human Effort","created":"2020-02-20","cited_by_count":111},{"id":"1812.02224","title":"Adapting Auxiliary Losses Using Gradient Similarity","created":"2018-12-05","cited_by_count":100},{"id":"1707.02747","title":"Robust Imitation of Diverse Behaviors","created":"2017-07-10","cited_by_count":86},{"id":"1909.09146","title":"Weighted Linear Bandits for Non-Stationary Environments","created":"2019-09-19","cited_by_count":86},{"id":"1602.07714","title":"Learning values across many orders of magnitude","created":"2016-02-24","cited_by_count":85},{"id":"1712.00378","title":"Time Limits in Reinforcement Learning","created":"2017-12-01","cited_by_count":79},{"id":"1902.10250","title":"Diagnosing Bottlenecks in Deep Q-learning Algorithms","created":"2019-02-26","cited_by_count":73},{"id":"1612.07307","title":"Loss is its own Reward: Self-Supervision for Reinforcement Learning","created":"2016-12-21","cited_by_count":72},{"id":"1902.00980","title":"A New Algorithm for Non-stationary Contextual Bandits: Efficient, Optimal, and Parameter-free","created":"2019-02-03","cited_by_count":71},{"id":"1705.08417","title":"Reinforcement Learning with a Corrupted Reward Channel","created":"2017-05-23","cited_by_count":70},{"id":"1708.01799","title":"Efficient Contextual Bandits in Non-stationary Worlds","created":"2017-08-05","cited_by_count":62},{"id":"1605.08478","title":"Model-Free Imitation Learning with Policy Optimization","created":"2016-05-26","cited_by_count":52},{"id":"2005.04305","title":"Measuring the Algorithmic Efficiency of Neural Networks","created":"2020-05-08","cited_by_count":52},{"id":"1610.01945","title":"Connecting Generative Adversarial Networks and Actor-Critic Methods","created":"2016-10-06","cited_by_count":50},{"id":"1903.01461","title":"Hedging the Drift: Learning to Optimize under Non-Stationarity","created":"2019-03-04","cited_by_count":46},{"id":"1903.08894","title":"Towards Characterizing Divergence in Deep Q-Learning","created":"2019-03-21","cited_by_count":43},{"id":"1911.00459","title":"Positive-Unlabeled Reward Learning","created":"2019-11-01","cited_by_count":37},{"id":"1904.10090","title":"Non-Stationary Markov Decision Processes, a Worst-Case Approach using Model-Based Reinforcement Learning, Extended version","created":"2019-04-22","cited_by_count":36},{"id":"1905.05857","title":"Variational Regret Bounds for Reinforcement Learning","created":"2019-05-14","cited_by_count":32},{"id":"1901.07510","title":"Understanding Multi-Step Deep Reinforcement Learning: A Systematic Study of the DQN Target","created":"2019-01-22","cited_by_count":31},{"id":"1805.10066","title":"A Sliding-Window Algorithm for Markov Decision Processes with Arbitrarily Changing Rewards and Transitions","created":"2018-05-25","cited_by_count":30},{"id":"1807.04720","title":"A Large-Scale Study on Regularization and Normalization in GANs","created":"2018-07-12","cited_by_count":26},{"id":"1603.00622","title":"PLATO: Policy Learning using Adaptive Trajectory Optimization","created":"2016-03-02","cited_by_count":24},{"id":"1303.3055","title":"Online Learning in Markov Decision Processes with Adversarially Chosen Transition Probability Distributions","created":"2013-03-12","cited_by_count":18},{"id":"1705.07215","title":"On Convergence and Stability of GANs","created":"2017-05-19","cited_by_count":18},{"id":"1805.03359","title":"Reward Estimation for Variance Reduction in Deep Reinforcement Learning","created":"2018-05-09","cited_by_count":17},{"id":"2003.02460","title":"A Closer Look at Accuracy vs. Robustness","created":"2020-03-05","cited_by_count":14},{"id":"1706.06617","title":"Observational Learning by Reinforcement Learning","created":"2017-06-20","cited_by_count":12},{"id":"1905.03970","title":"Reinforcement Learning in Non-Stationary Environments","created":"2019-05-10","cited_by_count":10},{"id":"1701.04271","title":"Fast Rates for Empirical Risk Minimization of Strict Saddle Problems","created":"2017-01-16","cited_by_count":7},{"id":"1705.05394","title":"Probabilistically Safe Policy Transfer","created":"2017-05-15","cited_by_count":6},{"id":"1907.09350","title":"Efficient Policy Learning for Non-Stationary MDPs under Adversarial Manipulation","created":"2019-07-22","cited_by_count":2}],"next_cursor":null}