{"list":"other","total":88,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"1706.06083","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","created":"2017-06-19","cited_by_count":6415},{"id":"1312.6199","title":"Intriguing properties of neural networks","created":"2013-12-21","cited_by_count":5155},{"id":"1706.04599","title":"On Calibration of Modern Neural Networks","created":"2017-06-14","cited_by_count":4960},{"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":"1509.02971","title":"Continuous control with deep reinforcement learning","created":"2015-09-09","cited_by_count":3407},{"id":"1606.03498","title":"Improved Techniques for Training GANs","created":"2016-06-10","cited_by_count":2970},{"id":"1502.05477","title":"Trust Region Policy Optimization","created":"2015-02-19","cited_by_count":2580},{"id":"1610.02136","title":"A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks","created":"2016-10-07","cited_by_count":2385},{"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":"1602.01783","title":"Asynchronous Methods for Deep Reinforcement Learning","created":"2016-02-04","cited_by_count":2258},{"id":"1611.03530","title":"Understanding deep learning requires rethinking generalization","created":"2016-11-10","cited_by_count":1674},{"id":"1606.06565","title":"Concrete Problems in AI Safety","created":"2016-06-21","cited_by_count":1642},{"id":"1606.03476","title":"Generative Adversarial Imitation Learning","created":"2016-06-10","cited_by_count":1597},{"id":"1703.06907","title":"Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World","created":"2017-03-20","cited_by_count":1498},{"id":"1702.08608","title":"Towards A Rigorous Science of Interpretable Machine Learning","created":"2017-02-28","cited_by_count":1416},{"id":"1806.01261","title":"Relational inductive biases, deep learning, and graph networks","created":"2018-06-04","cited_by_count":1360},{"id":"1711.11279","title":"Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)","created":"2017-11-30","cited_by_count":1319},{"id":"1802.00420","title":"Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples","created":"2018-02-01","cited_by_count":1268},{"id":"1705.10528","title":"Constrained Policy Optimization","created":"2017-05-30","cited_by_count":983},{"id":"1802.01561","title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures","created":"2018-02-05","cited_by_count":883},{"id":"1703.02910","title":"Deep Bayesian Active Learning with Image Data","created":"2017-03-08","cited_by_count":819},{"id":"1702.01135","title":"Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks","created":"2017-02-03","cited_by_count":744},{"id":"1505.05424","title":"Weight Uncertainty in Neural Networks","created":"2015-05-20","cited_by_count":554},{"id":"1703.11008","title":"Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data","created":"2017-03-31","cited_by_count":533},{"id":"1505.00853","title":"Empirical Evaluation of Rectified Activations in Convolutional Network","created":"2015-05-05","cited_by_count":519},{"id":"1506.02557","title":"Variational Dropout and the Local Reparameterization Trick","created":"2015-06-08","cited_by_count":490},{"id":"1807.00263","title":"Accurate Uncertainties for Deep Learning Using Calibrated Regression","created":"2018-07-01","cited_by_count":422},{"id":"1603.00448","title":"Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization","created":"2016-03-01","cited_by_count":406},{"id":"1805.00899","title":"AI safety via debate","created":"2018-05-02","cited_by_count":400},{"id":"1703.01161","title":"FeUdal Networks for Hierarchical Reinforcement Learning","created":"2017-03-03","cited_by_count":337},{"id":"1702.02284","title":"Adversarial Attacks on Neural Network Policies","created":"2017-02-08","cited_by_count":320},{"id":"1606.03137","title":"Cooperative Inverse Reinforcement Learning","created":"2016-06-09","cited_by_count":300},{"id":"1502.05336","title":"Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networks","created":"2015-02-18","cited_by_count":295},{"id":"1803.00933","title":"Distributed Prioritized Experience Replay","created":"2018-03-02","cited_by_count":269},{"id":"1807.01281","title":"Human-level performance in first-person multiplayer games with population-based deep reinforcement learning","created":"2018-07-03","cited_by_count":264},{"id":"1705.08439","title":"Thinking Fast and Slow with Deep Learning and Tree Search","created":"2017-05-23","cited_by_count":252},{"id":"1711.02827","title":"Inverse Reward Design","created":"2017-11-08","cited_by_count":249},{"id":"1705.07832","title":"Concrete Dropout","created":"2017-05-22","cited_by_count":227},{"id":"1801.01973","title":"A Note on the Inception Score","created":"2018-01-06","cited_by_count":226},{"id":"1802.05666","title":"Adversarial Risk and the Dangers of Evaluating Against Weak Attacks","created":"2018-02-15","cited_by_count":221},{"id":"1801.00631","title":"Deep Learning: A Critical Appraisal","created":"2018-01-02","cited_by_count":217},{"id":"1804.08617","title":"Distributed Distributional Deterministic Policy Gradients","created":"2018-04-23","cited_by_count":199},{"id":"1805.08328","title":"Verifiable Reinforcement Learning via Policy Extraction","created":"2018-05-22","cited_by_count":177},{"id":"1804.06893","title":"A Study on Overfitting in Deep Reinforcement Learning","created":"2018-04-18","cited_by_count":174},{"id":"1701.06049","title":"Interactive Learning from Policy-Dependent Human Feedback","created":"2017-01-21","cited_by_count":158},{"id":"1810.08575","title":"Supervising strong learners by amplifying weak experts","created":"2018-10-19","cited_by_count":145},{"id":"1805.12514","title":"Scaling provable adversarial defenses","created":"2018-05-31","cited_by_count":143},{"id":"1711.00138","title":"Visualizing and Understanding Atari Agents","created":"2017-10-31","cited_by_count":141},{"id":"1708.06374","title":"On a Formal Model of Safe and Scalable Self-driving Cars","created":"2017-08-21","cited_by_count":131},{"id":"1803.06567","title":"A Dual Approach to Scalable Verification of Deep Networks","created":"2018-03-17","cited_by_count":125},{"id":"1709.10163","title":"Deep TAMER: Interactive Agent Shaping in High-Dimensional State Spaces","created":"2017-09-28","cited_by_count":123},{"id":"1711.09883","title":"AI Safety Gridworlds","created":"2017-11-27","cited_by_count":110},{"id":"1703.01703","title":"Third-Person Imitation Learning","created":"2017-03-06","cited_by_count":103},{"id":"1707.05173","title":"Trial without Error: Towards Safe Reinforcement Learning via Human Intervention","created":"2017-07-17","cited_by_count":103},{"id":"1805.11592","title":"Playing hard exploration games by watching YouTube","created":"2018-05-29","cited_by_count":99},{"id":"1611.08219","title":"The Off-Switch Game","created":"2016-11-24","cited_by_count":97},{"id":"1803.03453","title":"The Surprising Creativity of Digital Evolution: A Collection of Anecdotes from the Evolutionary Computation and Artificial Life Research Communities","created":"2018-03-09","cited_by_count":78},{"id":"1711.00482","title":"Learning with Latent Language","created":"2017-11-01","cited_by_count":75},{"id":"1602.03506","title":"Research Priorities for Robust and Beneficial Artificial Intelligence","created":"2016-02-10","cited_by_count":74},{"id":"1705.08417","title":"Reinforcement Learning with a Corrupted Reward Channel","created":"2017-05-23","cited_by_count":70},{"id":"1808.00508","title":"Neural Arithmetic Logic Units","created":"2018-08-01","cited_by_count":70},{"id":"1602.02658","title":"Graying the black box: Understanding DQNs","created":"2016-02-08","cited_by_count":68},{"id":"1807.06732","title":"Motivating the Rules of the Game for Adversarial Example Research","created":"2018-07-18","cited_by_count":57},{"id":"1805.10265","title":"Training verified learners with learned verifiers","created":"2018-05-25","cited_by_count":50},{"id":"1512.05832","title":"Learning the Preferences of Ignorant, Inconsistent Agents","created":"2015-12-18","cited_by_count":45},{"id":"1712.05812","title":"Occam's razor is insufficient to infer the preferences of irrational agents","created":"2017-12-15","cited_by_count":45},{"id":"1809.08352","title":"Unrestricted Adversarial Examples","created":"2018-09-22","cited_by_count":40},{"id":"1806.01186","title":"Penalizing side effects using stepwise relative reachability","created":"2018-06-04","cited_by_count":38},{"id":"1805.11571","title":"Human-in-the-Loop Interpretability Prior","created":"2018-05-29","cited_by_count":36},{"id":"1704.06611","title":"Making Neural Programming Architectures Generalize via Recursion","created":"2017-04-21","cited_by_count":35},{"id":"1705.05427","title":"Repeated Inverse Reinforcement Learning","created":"2017-05-15","cited_by_count":29},{"id":"1805.01109","title":"AGI Safety Literature Review","created":"2018-05-03","cited_by_count":28},{"id":"1701.04079","title":"Agent-Agnostic Human-in-the-Loop Reinforcement Learning","created":"2017-01-15","cited_by_count":23},{"id":"1705.09990","title":"Should Robots be Obedient?","created":"2017-05-28","cited_by_count":20},{"id":"1510.04931","title":"Bad Universal Priors and Notions of Optimality","created":"2015-10-16","cited_by_count":16},{"id":"1609.03543","title":"Logical Induction","created":"2016-09-12","cited_by_count":16},{"id":"1704.06960","title":"Translating Neuralese","created":"2017-04-23","cited_by_count":16},{"id":"1809.04729","title":"A Less Biased Evaluation of Out-of-distribution Sample Detectors","created":"2018-09-13","cited_by_count":14},{"id":"1401.5577","title":"Robust Cooperation in the Prisoner's Dilemma: Program Equilibrium via Provability Logic","created":"2014-01-22","cited_by_count":13},{"id":"1804.10692","title":"Reward Learning from Narrated Demonstrations","created":"2018-04-27","cited_by_count":13},{"id":"1807.04950","title":"Deep Learning in the Wild","created":"2018-07-13","cited_by_count":12},{"id":"1705.10720","title":"Low Impact Artificial Intelligences","created":"2017-05-30","cited_by_count":11},{"id":"1803.04926","title":"Active Reinforcement Learning with Monte-Carlo Tree Search","created":"2018-03-13","cited_by_count":11},{"id":"1609.05058","title":"A Formal Solution to the Grain of Truth Problem","created":"2016-09-16","cited_by_count":6},{"id":"1712.01897","title":"Online Learning with Gated Linear Networks","created":"2017-12-05","cited_by_count":6}],"next_cursor":null}