{"list":"other","total":74,"rows":[{"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":"1711.03938","title":"CARLA: An Open Urban Driving Simulator","created":"2017-11-10","cited_by_count":2449},{"id":"1907.02893","title":"Invariant Risk Minimization","created":"2019-07-05","cited_by_count":1854},{"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":"1911.08731","title":"Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization","created":"2019-11-20","cited_by_count":1247},{"id":"1604.07316","title":"End to End Learning for Self-Driving Cars","created":"2016-04-25","cited_by_count":1009},{"id":"2004.04136","title":"CURL: Contrastive Unsupervised Representations for Reinforcement Learning","created":"2020-04-08","cited_by_count":760},{"id":"1802.05983","title":"Disentangling by Factorising","created":"2018-02-16","cited_by_count":616},{"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":"2009.12293","title":"robosuite: A Modular Simulation Framework and Benchmark for Robot Learning","created":"2020-09-25","cited_by_count":511},{"id":"1909.12434","title":"Learning the Difference that Makes a Difference with Counterfactually-Augmented Data","created":"2019-09-26","cited_by_count":439},{"id":"2006.10742","title":"Learning Invariant Representations for Reinforcement Learning without Reconstruction","created":"2020-06-18","cited_by_count":436},{"id":"2210.03094","title":"VIMA: General Robot Manipulation with Multimodal Prompts","created":"2022-10-06","cited_by_count":407},{"id":"2107.09645","title":"Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning","created":"2021-07-20","cited_by_count":372},{"id":"1905.11979","title":"Causal Confusion in Imitation Learning","created":"2019-05-28","cited_by_count":288},{"id":"1909.03683","title":"Don't Take the Easy Way Out: Ensemble Based Methods for Avoiding Known Dataset Biases","created":"2019-09-09","cited_by_count":280},{"id":"2003.08938","title":"Robust Deep Reinforcement Learning against Adversarial Perturbations on State Observations","created":"2020-03-19","cited_by_count":238},{"id":"1502.02259","title":"Contextual Markov Decision Processes","created":"2015-02-08","cited_by_count":220},{"id":"1810.05687","title":"Closing the Sim-to-Real Loop: Adapting Simulation Randomization with Real World Experience","created":"2018-10-12","cited_by_count":217},{"id":"2011.12945","title":"No Subclass Left Behind: Fine-Grained Robustness in Coarse-Grained Classification Problems","created":"2020-11-25","cited_by_count":209},{"id":"1812.07252","title":"Sim-to-Real via Sim-to-Sim: Data-efficient Robotic Grasping via Randomized-to-Canonical Adaptation Networks","created":"2018-12-18","cited_by_count":174},{"id":"1901.09184","title":"Action Robust Reinforcement Learning and Applications in Continuous Control","created":"2019-01-26","cited_by_count":174},{"id":"2203.01517","title":"Correct-N-Contrast: A Contrastive Approach for Improving Robustness to Spurious Correlations","created":"2022-03-03","cited_by_count":172},{"id":"1904.04762","title":"Active Domain Randomization","created":"2019-04-09","cited_by_count":170},{"id":"2107.14171","title":"Tianshou: a Highly Modularized Deep Reinforcement Learning Library","created":"2021-07-29","cited_by_count":143},{"id":"2011.13389","title":"Generalization in Reinforcement Learning by Soft Data Augmentation","created":"2020-11-26","cited_by_count":137},{"id":"2101.08452","title":"Robust Reinforcement Learning on State Observations with Learned Optimal Adversary","created":"2021-01-21","cited_by_count":135},{"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":"2109.14523","title":"Online Robust Reinforcement Learning with Model Uncertainty","created":"2021-09-29","cited_by_count":96},{"id":"2208.05129","title":"Robust Reinforcement Learning using Offline Data","created":"2022-08-10","cited_by_count":96},{"id":"2007.02863","title":"Counterfactual Data Augmentation using Locally Factored Dynamics","created":"2020-07-06","cited_by_count":93},{"id":"1803.00590","title":"Hierarchical Imitation and Reinforcement Learning","created":"2018-03-01","cited_by_count":88},{"id":"2208.05767","title":"Distributionally Robust Model-Based Offline Reinforcement Learning with Near-Optimal Sample Complexity","created":"2022-08-11","cited_by_count":87},{"id":"2112.01506","title":"Sample Complexity of Robust Reinforcement Learning with a Generative Model","created":"2021-12-02","cited_by_count":83},{"id":"2010.10814","title":"Improving Generalization in Reinforcement Learning with Mixture Regularization","created":"2020-10-21","cited_by_count":81},{"id":"2305.00650","title":"Discover and Cure: Concept-aware Mitigation of Spurious Correlation","created":"2023-05-01","cited_by_count":71},{"id":"1809.07731","title":"Benchmarking Reinforcement Learning Algorithms on Real-World Robots","created":"2018-09-20","cited_by_count":65},{"id":"2012.09092","title":"Sample-Efficient Reinforcement Learning via Counterfactual-Based Data Augmentation","created":"2020-12-16","cited_by_count":59},{"id":"2106.12723","title":"Meaningfully Debugging Model Mistakes using Conceptual Counterfactual Explanations","created":"2021-06-24","cited_by_count":53},{"id":"2205.15769","title":"Concept-level Debugging of Part-Prototype Networks","created":"2022-05-31","cited_by_count":52},{"id":"2305.16589","title":"The Curious Price of Distributional Robustness in Reinforcement Learning with a Generative Model","created":"2023-05-26","cited_by_count":52},{"id":"2305.09659","title":"Double Pessimism is Provably Efficient for Distributionally Robust Offline Reinforcement Learning: Generic Algorithm and Robust Partial Coverage","created":"2023-05-16","cited_by_count":51},{"id":"2006.09484","title":"Partial Policy Iteration for L1-Robust Markov Decision Processes","created":"2020-06-16","cited_by_count":50},{"id":"1810.02513","title":"Learning To Simulate","created":"2018-10-05","cited_by_count":44},{"id":"2108.02943","title":"Unsupervised Learning of Debiased Representations with Pseudo-Attributes","created":"2021-08-06","cited_by_count":44},{"id":"2210.11287","title":"MoCoDA: Model-based Counterfactual Data Augmentation","created":"2022-10-20","cited_by_count":44},{"id":"2303.02783","title":"Improved Sample Complexity Bounds for Distributionally Robust Reinforcement Learning","created":"2023-03-05","cited_by_count":44},{"id":"1904.02750","title":"DeceptionNet: Network-Driven Domain Randomization","created":"2019-04-04","cited_by_count":43},{"id":"1902.08708","title":"Distributionally Robust Reinforcement Learning","created":"2019-02-23","cited_by_count":42},{"id":"2003.02894","title":"Distributional Robustness and Regularization in Reinforcement Learning","created":"2020-03-05","cited_by_count":40},{"id":"2006.12311","title":"Provably Efficient Causal Reinforcement Learning with Confounded Observational Data","created":"2020-06-22","cited_by_count":40},{"id":"2106.02112","title":"Finding and Fixing Spurious Patterns with Explanations","created":"2021-06-03","cited_by_count":38},{"id":"2106.06196","title":"CausalAdv: Adversarial Robustness through the Lens of Causality","created":"2021-06-11","cited_by_count":37},{"id":"2302.13203","title":"A Finite Sample Complexity Bound for Distributionally Robust Q-learning","created":"2023-02-26","cited_by_count":36},{"id":"2207.09081","title":"Generalizing Goal-Conditioned Reinforcement Learning with Variational Causal Reasoning","created":"2022-07-19","cited_by_count":34},{"id":"2007.11500","title":"Debiasing Concept-based Explanations with Causal Analysis","created":"2020-07-22","cited_by_count":32},{"id":"2209.06620","title":"Distributionally Robust Offline Reinforcement Learning with Linear Function Approximation","created":"2022-09-14","cited_by_count":32},{"id":"2007.07176","title":"Robustifying Reinforcement Learning Agents via Action Space Adversarial Training","created":"2020-07-14","cited_by_count":30},{"id":"2305.18420","title":"Sample Complexity of Variance-reduced Distributionally Robust Q-learning","created":"2023-05-28","cited_by_count":29},{"id":"2212.02705","title":"What is the Solution for State-Adversarial Multi-Agent Reinforcement Learning?","created":"2022-12-06","cited_by_count":22},{"id":"2302.05372","title":"Towards Minimax Optimality of Model-based Robust Reinforcement Learning","created":"2023-02-10","cited_by_count":22},{"id":"2110.10735","title":"Dynamic Bottleneck for Robust Self-Supervised Exploration","created":"2021-10-20","cited_by_count":21},{"id":"2209.13841","title":"Online Policy Optimization for Robust MDP","created":"2022-09-28","cited_by_count":19},{"id":"2202.07013","title":"Robust Policy Learning over Multiple Uncertainty Sets","created":"2022-02-14","cited_by_count":18},{"id":"2110.14118","title":"Object-Aware Regularization for Addressing Causal Confusion in Imitation Learning","created":"2021-10-27","cited_by_count":17},{"id":"2301.11721","title":"Single-Trajectory Distributionally Robust Reinforcement Learning","created":"2023-01-27","cited_by_count":16},{"id":"2103.10972","title":"Learning Task Decomposition with Ordered Memory Policy Network","created":"2021-03-19","cited_by_count":15},{"id":"2110.06539","title":"On Covariate Shift of Latent Confounders in Imitation and Reinforcement Learning","created":"2021-10-13","cited_by_count":14},{"id":"2109.08776","title":"Exploring the Training Robustness of Distributional Reinforcement Learning against Noisy State Observations","created":"2021-09-17","cited_by_count":12},{"id":"2211.08285","title":"Identifying Spurious Correlations and Correcting them with an Explanation-based Learning","created":"2022-11-15","cited_by_count":10},{"id":"2110.12468","title":"False Correlation Reduction for Offline Reinforcement Learning","created":"2021-10-24","cited_by_count":9},{"id":"2206.07188","title":"Defending Observation Attacks in Deep Reinforcement Learning via Detection and Denoising","created":"2022-06-14","cited_by_count":8},{"id":"2210.12262","title":"Group Distributionally Robust Reinforcement Learning with Hierarchical Latent Variables","created":"2022-10-21","cited_by_count":7},{"id":"2204.06173","title":"Synthesizing Adversarial Visual Scenarios for Model-Based Robotic Control","created":"2022-04-13","cited_by_count":4}],"next_cursor":null}