{"list":"other","total":51,"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":"1509.06461","title":"Deep Reinforcement Learning with Double Q-learning","created":"2015-09-22","cited_by_count":1745},{"id":"2106.01345","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","created":"2021-06-02","cited_by_count":1546},{"id":"1705.05363","title":"Curiosity-driven Exploration by Self-supervised Prediction","created":"2017-05-15","cited_by_count":1194},{"id":"1710.02298","title":"Rainbow: Combining Improvements in Deep Reinforcement Learning","created":"2017-10-06","cited_by_count":786},{"id":"2004.04136","title":"CURL: Contrastive Unsupervised Representations for Reinforcement Learning","created":"2020-04-08","cited_by_count":760},{"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":"1903.00374","title":"Model-Based Reinforcement Learning for Atari","created":"2019-03-01","cited_by_count":502},{"id":"2004.14990","title":"Reinforcement Learning with Augmented Data","created":"2020-04-30","cited_by_count":468},{"id":"1507.06527","title":"Deep Recurrent Q-Learning for Partially Observable MDPs","created":"2015-07-23","cited_by_count":465},{"id":"1704.06888","title":"Time-Contrastive Networks: Self-Supervised Learning from Video","created":"2017-04-23","cited_by_count":459},{"id":"1812.02341","title":"Quantifying Generalization in Reinforcement Learning","created":"2018-12-06","cited_by_count":352},{"id":"2003.13350","title":"Agent57: Outperforming the Atari Human Benchmark","created":"2020-03-30","cited_by_count":303},{"id":"2009.08319","title":"Decoupling Representation Learning from Reinforcement Learning","created":"2020-09-14","cited_by_count":269},{"id":"1706.10295","title":"Noisy Networks for Exploration","created":"2017-06-30","cited_by_count":266},{"id":"1309.6779","title":"Causal Discovery with Continuous Additive Noise Models","created":"2013-09-26","cited_by_count":255},{"id":"2206.07568","title":"Contrastive Learning as Goal-Conditioned Reinforcement Learning","created":"2022-06-15","cited_by_count":253},{"id":"2205.07802","title":"The Primacy Bias in Deep Reinforcement Learning","created":"2022-05-16","cited_by_count":247},{"id":"1702.07007","title":"Detecting causal associations in large nonlinear time series datasets","created":"2017-02-22","cited_by_count":244},{"id":"2002.00498","title":"DYNOTEARS: Structure Learning from Time-Series Data","created":"2020-02-02","cited_by_count":200},{"id":"2202.05607","title":"Online Decision Transformer","created":"2022-02-11","cited_by_count":196},{"id":"1804.06893","title":"A Study on Overfitting in Deep Reinforcement Learning","created":"2018-04-18","cited_by_count":174},{"id":"2302.12902","title":"The Dormant Neuron Phenomenon in Deep Reinforcement Learning","created":"2023-02-24","cited_by_count":174},{"id":"2209.11924","title":"Interventional Causal Representation Learning","created":"2022-09-24","cited_by_count":142},{"id":"2003.03685","title":"Discovering contemporaneous and lagged causal relations in autocorrelated nonlinear time series datasets","created":"2020-03-07","cited_by_count":137},{"id":"1802.04181","title":"State Representation Learning for Control: An Overview","created":"2018-02-12","cited_by_count":127},{"id":"2306.00542","title":"Nonparametric Identifiability of Causal Representations from Unknown Interventions","created":"2023-06-01","cited_by_count":106},{"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":"2006.10833","title":"Amortized Causal Discovery: Learning to Infer Causal Graphs from Time-Series Data","created":"2020-06-18","cited_by_count":100},{"id":"2402.05052","title":"Causal Representation Learning from Multiple Distributions: A General Setting","created":"2024-02-07","cited_by_count":68},{"id":"2206.13452","title":"Causal Dynamics Learning for Task-Independent State Abstraction","created":"2022-06-27","cited_by_count":65},{"id":"2201.07779","title":"Look Closer: Bridging Egocentric and Third-Person Views with Transformers for Robotic Manipulation","created":"2022-01-19","cited_by_count":49},{"id":"2101.07600","title":"Interpretable Models for Granger Causality Using Self-explaining Neural Networks","created":"2021-01-19","cited_by_count":45},{"id":"2105.02522","title":"Neural graphical modelling in continuous-time: consistency guarantees and algorithms","created":"2021-05-06","cited_by_count":42},{"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":"2003.01629","title":"Can Increasing Input Dimensionality Improve Deep Reinforcement Learning?","created":"2020-03-03","cited_by_count":37},{"id":"2106.02988","title":"Causal Bandits with Unknown Graph Structure","created":"2021-06-05","cited_by_count":37},{"id":"2303.15027","title":"A Survey on Causal Discovery Methods for I.I.D. and Time Series Data","created":"2023-03-27","cited_by_count":35},{"id":"2310.15450","title":"General Identifiability and Achievability for Causal Representation Learning","created":"2023-10-24","cited_by_count":34},{"id":"2109.04286","title":"NTS-NOTEARS: Learning Nonparametric DBNs With Prior Knowledge","created":"2021-09-09","cited_by_count":33},{"id":"2002.01751","title":"Does the Markov Decision Process Fit the Data: Testing for the Markov Property in Sequential Decision Making","created":"2020-02-05","cited_by_count":30},{"id":"2106.07643","title":"Unsupervised Learning of Visual 3D Keypoints for Control","created":"2021-06-14","cited_by_count":30},{"id":"2511.11478","title":"Rethinking Progression of Memory State in Robotic Manipulation: An Object-Centric Perspective","created":"2025-11-14","cited_by_count":20},{"id":"2506.16507","title":"Robust Reward Modeling via Causal Rubrics","created":"2025-06-19","cited_by_count":19},{"id":"2306.12896","title":"Causal discovery for time series from multiple datasets with latent contexts","created":"2023-06-22","cited_by_count":16},{"id":"1910.08285","title":"Multi-View Reinforcement Learning","created":"2019-10-18","cited_by_count":12},{"id":"2305.19244","title":"Testing for the Markov Property in Time Series via Deep Conditional Generative Learning","created":"2023-05-30","cited_by_count":9},{"id":"2410.14659","title":"Harnessing Causality in Reinforcement Learning With Bagged Decision Times","created":"2024-10-18","cited_by_count":5},{"id":"2506.07844","title":"Conditional Local Independence Testing for It\\^o processes with Applications to Dynamic Causal Discovery","created":"2025-06-09","cited_by_count":1}],"next_cursor":null}