{"list":"other","total":119,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"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":"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":"1711.03938","title":"CARLA: An Open Urban Driving Simulator","created":"2017-11-10","cited_by_count":2449},{"id":"1602.01783","title":"Asynchronous Methods for Deep Reinforcement Learning","created":"2016-02-04","cited_by_count":2258},{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920},{"id":"1509.06461","title":"Deep Reinforcement Learning with Double Q-learning","created":"2015-09-22","cited_by_count":1745},{"id":"1511.06581","title":"Dueling Network Architectures for Deep Reinforcement Learning","created":"2015-11-20","cited_by_count":785},{"id":"1805.12114","title":"Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models","created":"2018-05-30","cited_by_count":774},{"id":"1906.08253","title":"When to Trust Your Model: Model-Based Policy Optimization","created":"2019-06-19","cited_by_count":773},{"id":"1709.06560","title":"Deep Reinforcement Learning that Matters","created":"2017-09-19","cited_by_count":754},{"id":"1705.08926","title":"Counterfactual Multi-Agent Policy Gradients","created":"2017-05-24","cited_by_count":751},{"id":"2005.13239","title":"MOPO: Model-based Offline Policy Optimization","created":"2020-05-27","cited_by_count":636},{"id":"1706.03461","title":"Meta-learners for Estimating Heterogeneous Treatment Effects using Machine Learning","created":"2017-06-12","cited_by_count":478},{"id":"1811.06711","title":"An Algorithmic Perspective on Imitation Learning","created":"2018-11-16","cited_by_count":459},{"id":"2006.10742","title":"Learning Invariant Representations for Reinforcement Learning without Reconstruction","created":"2020-06-18","cited_by_count":436},{"id":"1603.00448","title":"Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization","created":"2016-03-01","cited_by_count":406},{"id":"2102.08363","title":"COMBO: Conservative Offline Model-Based Policy Optimization","created":"2021-02-16","cited_by_count":370},{"id":"1904.08980","title":"Exploring the Limitations of Behavior Cloning for Autonomous Driving","created":"2019-04-18","cited_by_count":346},{"id":"1701.07274","title":"Deep Reinforcement Learning: An Overview","created":"2017-01-25","cited_by_count":333},{"id":"1712.04912","title":"Quasi-Oracle Estimation of Heterogeneous Treatment Effects","created":"2017-12-13","cited_by_count":332},{"id":"1605.03661","title":"Learning Representations for Counterfactual Inference","created":"2016-05-12","cited_by_count":329},{"id":"1908.08796","title":"Reinforcement Learning in Healthcare: A Survey","created":"2019-08-22","cited_by_count":310},{"id":"1708.02596","title":"Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuning","created":"2017-08-08","cited_by_count":297},{"id":"1905.11979","title":"Causal Confusion in Imitation Learning","created":"2019-05-28","cited_by_count":288},{"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":"1802.10592","title":"Model-Ensemble Trust-Region Policy Optimization","created":"2018-02-28","cited_by_count":219},{"id":"2002.02770","title":"A Survey on Causal Inference","created":"2020-02-05","cited_by_count":202},{"id":"1302.6815","title":"Learning Bayesian Networks: The Combination of Knowledge and Statistical Data","created":"2013-02-27","cited_by_count":187},{"id":"1905.10958","title":"Explainable Reinforcement Learning Through a Causal Lens","created":"2019-05-27","cited_by_count":177},{"id":"1302.4983","title":"Causal Inference in the Presence of Latent Variables and Selection Bias","created":"2013-02-20","cited_by_count":166},{"id":"1903.01672","title":"Causal Discovery from Heterogeneous/Nonstationary Data with Independent Changes","created":"2019-03-05","cited_by_count":166},{"id":"1703.01988","title":"Neural Episodic Control","created":"2017-03-06","cited_by_count":151},{"id":"1609.08816","title":"Identifying Causal Effects With Proxy Variables of an Unmeasured Confounder","created":"2016-09-28","cited_by_count":139},{"id":"1905.05824","title":"Counterfactual Off-Policy Evaluation with Gumbel-Max Structural Causal Models","created":"2019-05-14","cited_by_count":117},{"id":"2204.12581","title":"RAMBO-RL: Robust Adversarial Model-Based Offline Reinforcement Learning","created":"2022-04-26","cited_by_count":115},{"id":"2206.15475","title":"Causal Machine Learning: A Survey and Open Problems","created":"2022-06-30","cited_by_count":110},{"id":"2010.04296","title":"CausalWorld: A Robotic Manipulation Benchmark for Causal Structure and Transfer Learning","created":"2020-10-08","cited_by_count":109},{"id":"2003.06016","title":"Invariant Causal Prediction for Block MDPs","created":"2020-03-12","cited_by_count":105},{"id":"1606.03203","title":"Causal Bandits: Learning Good Interventions via Causal Inference","created":"2016-06-10","cited_by_count":101},{"id":"2007.02863","title":"Counterfactual Data Augmentation using Locally Factored Dynamics","created":"2020-07-06","cited_by_count":93},{"id":"2007.01884","title":"High-recall causal discovery for autocorrelated time series with latent confounders","created":"2020-07-03","cited_by_count":84},{"id":"1811.06272","title":"Woulda, Coulda, Shoulda: Counterfactually-Guided Policy Search","created":"2018-11-15","cited_by_count":82},{"id":"1805.10000","title":"Virtual-Taobao: Virtualizing Real-world Online Retail Environment for Reinforcement Learning","created":"2018-05-25","cited_by_count":80},{"id":"1805.08593","title":"Confounding-Robust Policy Improvement","created":"2018-05-22","cited_by_count":76},{"id":"2010.14876","title":"Fighting Copycat Agents in Behavioral Cloning from Observation Histories","created":"2020-10-28","cited_by_count":71},{"id":"2106.03443","title":"Causal Influence Detection for Improving Efficiency in Reinforcement Learning","created":"2021-06-07","cited_by_count":71},{"id":"1909.03739","title":"Off-Policy Evaluation in Partially Observable Environments","created":"2019-09-09","cited_by_count":66},{"id":"2206.09328","title":"A Survey on Model-based Reinforcement Learning","created":"2022-06-19","cited_by_count":66},{"id":"2206.13452","title":"Causal Dynamics Learning for Task-Independent State Abstraction","created":"2022-06-27","cited_by_count":65},{"id":"2003.05623","title":"Off-policy Policy Evaluation For Sequential Decisions Under Unobserved Confounding","created":"2020-03-12","cited_by_count":61},{"id":"2012.09092","title":"Sample-Efficient Reinforcement Learning via Counterfactual-Based Data Augmentation","created":"2020-12-16","cited_by_count":59},{"id":"1706.04317","title":"Schema Networks: Zero-shot Transfer with a Generative Causal Model of Intuitive Physics","created":"2017-06-14","cited_by_count":58},{"id":"1807.09341","title":"Learning Plannable Representations with Causal InfoGAN","created":"2018-07-24","cited_by_count":57},{"id":"2002.04518","title":"Confounding-Robust Policy Evaluation in Infinite-Horizon Reinforcement Learning","created":"2020-02-11","cited_by_count":57},{"id":"1901.08162","title":"Causal Reasoning from Meta-reinforcement Learning","created":"2019-01-23","cited_by_count":53},{"id":"2010.03110","title":"Causal Curiosity: RL Agents Discovering Self-supervised Experiments for Causal Representation Learning","created":"2020-10-07","cited_by_count":53},{"id":"2107.02729","title":"AdaRL: What, Where, and How to Adapt in Transfer Reinforcement Learning","created":"2021-07-06","cited_by_count":48},{"id":"1807.07665","title":"Hierarchical Reinforcement Learning for Zero-shot Generalization with Subtask Dependencies","created":"2018-07-19","cited_by_count":43},{"id":"2007.13893","title":"Off-policy Evaluation in Infinite-Horizon Reinforcement Learning with Latent Confounders","created":"2020-07-27","cited_by_count":41},{"id":"2110.15332","title":"Proximal Reinforcement Learning: Efficient Off-Policy Evaluation in Partially Observed Markov Decision Processes","created":"2021-10-28","cited_by_count":41},{"id":"2208.06267","title":"Causal Imitation Learning with Unobserved Confounders","created":"2022-08-12","cited_by_count":41},{"id":"2006.12311","title":"Provably Efficient Causal Reinforcement Learning with Confounded Observational Data","created":"2020-06-22","cited_by_count":40},{"id":"2106.03907","title":"Deep Proxy Causal Learning and its Application to Confounded Bandit Policy Evaluation","created":"2021-06-07","cited_by_count":40},{"id":"1701.02789","title":"Identifying Best Interventions through Online Importance Sampling","created":"2017-01-10","cited_by_count":39},{"id":"2012.07058","title":"Budgeted and Non-budgeted Causal Bandits","created":"2020-12-13","cited_by_count":38},{"id":"2006.01096","title":"Invariant Policy Optimization: Towards Stronger Generalization in Reinforcement Learning","created":"2020-06-01","cited_by_count":37},{"id":"2106.02988","title":"Causal Bandits with Unknown Graph Structure","created":"2021-06-05","cited_by_count":37},{"id":"1812.10576","title":"Deconfounding Reinforcement Learning in Observational Settings","created":"2018-12-26","cited_by_count":36},{"id":"2111.06784","title":"A Minimax Learning Approach to Off-Policy Evaluation in Confounded Partially Observable Markov Decision Processes","created":"2021-11-12","cited_by_count":36},{"id":"2102.09907","title":"Instrumental Variable Value Iteration for Causal Offline Reinforcement Learning","created":"2021-02-19","cited_by_count":35},{"id":"2207.09081","title":"Generalizing Goal-Conditioned Reinforcement Learning with Variational Causal Reasoning","created":"2022-07-19","cited_by_count":34},{"id":"1910.01751","title":"Causal Induction from Visual Observations for Goal Directed Tasks","created":"2019-10-03","cited_by_count":31},{"id":"2110.05721","title":"Action-Sufficient State Representation Learning for Control with Structural Constraints","created":"2021-10-12","cited_by_count":31},{"id":"2202.10589","title":"Off-Policy Confidence Interval Estimation with Confounded Markov Decision Process","created":"2022-02-22","cited_by_count":31},{"id":"1906.10437","title":"Learning Causal State Representations of Partially Observable Environments","created":"2019-06-25","cited_by_count":30},{"id":"2203.16582","title":"Factored Adaptation for Non-Stationary Reinforcement Learning","created":"2022-03-30","cited_by_count":30},{"id":"1303.7410","title":"ParceLiNGAM: A causal ordering method robust against latent confounders","created":"2013-03-29","cited_by_count":29},{"id":"2202.01312","title":"Causal Imitation Learning under Temporally Correlated Noise","created":"2022-02-02","cited_by_count":28},{"id":"2106.06452","title":"Keyframe-Focused Visual Imitation Learning","created":"2021-06-11","cited_by_count":25},{"id":"2208.06276","title":"Sequential Causal Imitation Learning with Unobserved Confounders","created":"2022-08-12","cited_by_count":25},{"id":"2002.02836","title":"Causally Correct Partial Models for Reinforcement Learning","created":"2020-02-07","cited_by_count":24},{"id":"2110.12343","title":"Off-Policy Evaluation in Partially Observed Markov Decision Processes under Sequential Ignorability","created":"2021-10-24","cited_by_count":24},{"id":"2210.06964","title":"Causality-driven Hierarchical Structure Discovery for Reinforcement Learning","created":"2022-10-13","cited_by_count":24},{"id":"1806.02252","title":"Causal Bandits with Propagating Inference","created":"2018-06-06","cited_by_count":23},{"id":"2006.06731","title":"Bandits with Partially Observable Confounded Data","created":"2020-06-11","cited_by_count":22},{"id":"2103.16772","title":"Causal Reasoning in Simulation for Structure and Transfer Learning of Robot Manipulation Policies","created":"2021-03-31","cited_by_count":22},{"id":"2105.10148","title":"On Instrumental Variable Regression for Deep Offline Policy Evaluation","created":"2021-05-21","cited_by_count":22},{"id":"2109.10502","title":"A Spectral Approach to Off-Policy Evaluation for POMDPs","created":"2021-09-22","cited_by_count":21},{"id":"2206.01474","title":"Offline Reinforcement Learning with Causal Structured World Models","created":"2022-06-03","cited_by_count":19},{"id":"2102.09850","title":"Model-Invariant State Abstractions for Model-Based Reinforcement Learning","created":"2021-02-19","cited_by_count":18},{"id":"2109.10665","title":"A Survey on Reinforcement Learning for Recommender Systems","created":"2021-09-22","cited_by_count":18},{"id":"2106.00808","title":"Invariant Policy Learning: A Causal Perspective","created":"2021-06-01","cited_by_count":17},{"id":"1907.06584","title":"Environment Reconstruction with Hidden Confounders for Reinforcement Learning based Recommendation","created":"2019-07-12","cited_by_count":16},{"id":"2111.06721","title":"Causal Multi-Agent Reinforcement Learning: Review and Open Problems","created":"2021-11-12","cited_by_count":16},{"id":"2206.04551","title":"A Relational Intervention Approach for Unsupervised Dynamics Generalization in Model-Based Reinforcement Learning","created":"2022-06-09","cited_by_count":15},{"id":"2206.10816","title":"Fighting Fire with Fire: Avoiding DNN Shortcuts through Priming","created":"2022-06-22","cited_by_count":15},{"id":"2002.05217","title":"Resolving Spurious Correlations in Causal Models of Environments via Interventions","created":"2020-02-12","cited_by_count":14}],"next_cursor":"100"}