{"list":"other","total":56,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1312.6199","title":"Intriguing properties of neural networks","created":"2013-12-21","cited_by_count":5155},{"id":"1502.05477","title":"Trust Region Policy Optimization","created":"2015-02-19","cited_by_count":2580},{"id":"1802.09477","title":"Addressing Function Approximation Error in Actor-Critic Methods","created":"2018-02-26","cited_by_count":2417},{"id":"1509.06461","title":"Deep Reinforcement Learning with Double Q-learning","created":"2015-09-22","cited_by_count":1745},{"id":"1911.08265","title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","created":"2019-11-19","cited_by_count":1353},{"id":"2108.13264","title":"Deep Reinforcement Learning at the Edge of the Statistical Precipice","created":"2021-08-30","cited_by_count":807},{"id":"1511.06581","title":"Dueling Network Architectures for Deep Reinforcement Learning","created":"2015-11-20","cited_by_count":785},{"id":"2004.04136","title":"CURL: Contrastive Unsupervised Representations for Reinforcement Learning","created":"2020-04-08","cited_by_count":760},{"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":"1912.01588","title":"Leveraging Procedural Generation to Benchmark Reinforcement Learning","created":"2019-12-03","cited_by_count":483},{"id":"2004.14990","title":"Reinforcement Learning with Augmented Data","created":"2020-04-30","cited_by_count":468},{"id":"1703.02702","title":"Robust Adversarial Reinforcement Learning","created":"2017-03-08","cited_by_count":451},{"id":"1812.02341","title":"Quantifying Generalization in Reinforcement Learning","created":"2018-12-06","cited_by_count":352},{"id":"1606.05312","title":"Successor Features for Transfer in Reinforcement Learning","created":"2016-06-16","cited_by_count":340},{"id":"1702.02284","title":"Adversarial Attacks on Neural Network Policies","created":"2017-02-08","cited_by_count":320},{"id":"2012.02096","title":"Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Design","created":"2020-12-03","cited_by_count":275},{"id":"1706.10295","title":"Noisy Networks for Exploration","created":"2017-06-30","cited_by_count":266},{"id":"2003.08938","title":"Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations","created":"2020-03-19","cited_by_count":238},{"id":"1905.10615","title":"Adversarial Policies: Attacking Deep Reinforcement Learning","created":"2019-05-25","cited_by_count":214},{"id":"2106.12142","title":"IQ-Learn: Inverse soft-Q Learning for Imitation","created":"2021-06-23","cited_by_count":193},{"id":"1703.06748","title":"Tactics of Adversarial Attack on Deep Reinforcement Learning Agents","created":"2017-03-08","cited_by_count":166},{"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":"2009.04416","title":"Phasic Policy Gradient","created":"2020-09-09","cited_by_count":123},{"id":"2101.05265","title":"Contrastive Behavioral Similarity Embeddings for Generalization in Reinforcement Learning","created":"2021-01-13","cited_by_count":123},{"id":"2105.10919","title":"Continual World: A Robotic Benchmark For Continual Reinforcement Learning","created":"2021-05-23","cited_by_count":116},{"id":"1402.0635","title":"Generalization and Exploration via Randomized Value Functions","created":"2014-02-04","cited_by_count":112},{"id":"1611.01929","title":"Averaged-DQN: Variance Reduction and Stabilization for Deep Reinforcement Learning","created":"2016-11-07","cited_by_count":106},{"id":"1705.06452","title":"Delving into adversarial attacks on deep policies","created":"2017-05-18","cited_by_count":104},{"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":"2102.10330","title":"Decoupling Value and Policy for Generalization in Reinforcement Learning","created":"2021-02-20","cited_by_count":82},{"id":"2010.10814","title":"Improving Generalization in Reinforcement Learning with Mixture Regularization","created":"2020-10-21","cited_by_count":81},{"id":"2007.08794","title":"Discovering Reinforcement Learning Algorithms","created":"2020-07-17","cited_by_count":77},{"id":"2007.14430","title":"Munchausen Reinforcement Learning","created":"2020-07-28","cited_by_count":69},{"id":"2007.08433","title":"Meta-Gradient Reinforcement Learning with an Objective Discovered Online","created":"2020-07-16","cited_by_count":52},{"id":"1806.07377","title":"Transfer Learning for Related Reinforcement Learning Tasks via Image-to-Image Translation","created":"2018-05-31","cited_by_count":50},{"id":"2007.02040","title":"Discount Factor as a Regularizer in Reinforcement Learning","created":"2020-07-04","cited_by_count":45},{"id":"2209.07550","title":"Human-level Atari 200x faster","created":"2022-09-15","cited_by_count":28},{"id":"2102.06741","title":"Discovery of Options via Meta-Learned Subgoals","created":"2021-02-12","cited_by_count":27},{"id":"2102.01514","title":"Metrics and continuity in reinforcement learning","created":"2021-02-02","cited_by_count":26},{"id":"2011.01928","title":"Generalization to New Actions in Reinforcement Learning","created":"2020-11-03","cited_by_count":25},{"id":"2109.10781","title":"Introducing Symmetries to Black Box Meta Reinforcement Learning","created":"2021-09-22","cited_by_count":25},{"id":"2001.05411","title":"Lipschitz Lifelong Reinforcement Learning","created":"2020-01-15","cited_by_count":23},{"id":"2101.00300","title":"When Is Generalizable Reinforcement Learning Tractable?","created":"2021-01-01","cited_by_count":20},{"id":"1912.02807","title":"Combining Q-Learning and Search with Amortized Value Estimates","created":"2019-12-05","cited_by_count":19},{"id":"2301.07487","title":"Adversarial Robust Deep Reinforcement Learning Requires Redefining Robustness","created":"2023-01-17","cited_by_count":19},{"id":"1902.00843","title":"A Meta-MDP Approach to Exploration for Lifelong Reinforcement Learning","created":"2019-02-03","cited_by_count":18},{"id":"1906.01770","title":"Lifelong Learning with a Changing Action Set","created":"2019-06-05","cited_by_count":17},{"id":"2108.13093","title":"Investigating Vulnerabilities of Deep Neural Policies","created":"2021-08-30","cited_by_count":15},{"id":"2112.09025","title":"Deep Reinforcement Learning Policies Learn Shared Adversarial Features Across MDPs","created":"2021-12-16","cited_by_count":12},{"id":"2306.05873","title":"Detecting Adversarial Directions in Deep Reinforcement Learning to Make Robust Decisions","created":"2023-06-09","cited_by_count":7}],"next_cursor":null}