{"list":"other","total":56,"rows":[{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"id":"1412.3555","title":"Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling","created":"2014-12-11","cited_by_count":2367},{"id":"1906.00446","title":"Generating Diverse High-Fidelity Images with VQ-VAE-2","created":"2019-06-02","cited_by_count":1387},{"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":"1611.00712","title":"The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables","created":"2016-11-02","cited_by_count":1148},{"id":"2009.12293","title":"robosuite: A Modular Simulation Framework and Benchmark for Robot Learning","created":"2020-09-25","cited_by_count":511},{"id":"1903.00374","title":"Model-Based Reinforcement Learning for Atari","created":"2019-03-01","cited_by_count":502},{"id":"1905.11979","title":"Causal Confusion in Imitation Learning","created":"2019-05-28","cited_by_count":288},{"id":"1909.10893","title":"Recurrent Independent Mechanisms","created":"2019-09-24","cited_by_count":219},{"id":"2007.01754","title":"Differentiable Causal Discovery from Interventional Data","created":"2020-07-03","cited_by_count":218},{"id":"1911.12247","title":"Contrastive Learning of Structured World Models","created":"2019-11-27","cited_by_count":209},{"id":"1905.10958","title":"Explainable Reinforcement Learning Through a Causal Lens","created":"2019-05-27","cited_by_count":177},{"id":"1905.05824","title":"Counterfactual Off-Policy Evaluation with Gumbel-Max Structural Causal Models","created":"2019-05-14","cited_by_count":117},{"id":"2003.06016","title":"Invariant Causal Prediction for Block MDPs","created":"2020-03-12","cited_by_count":105},{"id":"2007.02863","title":"Counterfactual Data Augmentation using Locally Factored Dynamics","created":"2020-07-06","cited_by_count":93},{"id":"1811.06272","title":"Woulda, Coulda, Shoulda: Counterfactually-Guided Policy Search","created":"2018-11-15","cited_by_count":82},{"id":"2007.00631","title":"Causal Discovery in Physical Systems from Videos","created":"2020-07-01","cited_by_count":77},{"id":"1802.06310","title":"Characterizing and Learning Equivalence Classes of Causal DAGs under Interventions","created":"2018-02-17","cited_by_count":76},{"id":"2103.01937","title":"Neural Production Systems: Learning Rule-Governed Visual Dynamics","created":"2021-03-02","cited_by_count":75},{"id":"2106.03443","title":"Causal Influence Detection for Improving Efficiency in Reinforcement Learning","created":"2021-06-07","cited_by_count":71},{"id":"2205.07547","title":"SQ-VAE: Variational Bayes on Discrete Representation with Self-annealed Stochastic Quantization","created":"2022-05-16","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":"2011.09464","title":"Counterfactual Credit Assignment in Model-Free Reinforcement Learning","created":"2020-11-18","cited_by_count":64},{"id":"2012.09092","title":"Sample-Efficient Reinforcement Learning via Counterfactual-Based Data Augmentation","created":"2020-12-16","cited_by_count":59},{"id":"2002.08111","title":"Hierarchical Quantized Autoencoders","created":"2020-02-19","cited_by_count":57},{"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":"2107.00848","title":"Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learning","created":"2021-07-02","cited_by_count":53},{"id":"2302.04419","title":"An Investigation into Pre-Training Object-Centric Representations for Reinforcement Learning","created":"2023-02-09","cited_by_count":49},{"id":"2106.04615","title":"Vector Quantized Models for Planning","created":"2021-06-08","cited_by_count":48},{"id":"2011.14381","title":"Self-supervised Visual Reinforcement Learning with Object-centric Representations","created":"2020-11-29","cited_by_count":44},{"id":"2210.11287","title":"MoCoDA: Model-based Counterfactual Data Augmentation","created":"2022-10-20","cited_by_count":44},{"id":"1302.3562","title":"Context-Specific Independence in Bayesian Networks","created":"2013-02-13","cited_by_count":43},{"id":"2208.06267","title":"Causal Imitation Learning with Unobserved Confounders","created":"2022-08-12","cited_by_count":41},{"id":"1812.10576","title":"Deconfounding Reinforcement Learning in Observational Settings","created":"2018-12-26","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":"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":"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":"2208.06276","title":"Sequential Causal Imitation Learning with Unobserved Confounders","created":"2022-08-12","cited_by_count":25},{"id":"1803.08784","title":"Causal Modeling of Dynamical Systems","created":"2018-03-23","cited_by_count":24},{"id":"2002.02836","title":"Causally Correct Partial Models for Reinforcement Learning","created":"2020-02-07","cited_by_count":24},{"id":"2009.09768","title":"Identifying Causal Effects via Context-specific Independence Relations","created":"2020-09-21","cited_by_count":22},{"id":"2007.13202","title":"CAMPs: Learning Context-Specific Abstractions for Efficient Planning in Factored MDPs","created":"2020-07-26","cited_by_count":18},{"id":"2102.09850","title":"Model-Invariant State Abstractions for Model-Based Reinforcement Learning","created":"2021-02-19","cited_by_count":18},{"id":"2307.09205","title":"Learning Dynamic Attribute-factored World Models for Efficient Multi-object Reinforcement Learning","created":"2023-07-18","cited_by_count":15},{"id":"2311.01489","title":"Invariant Causal Imitation Learning for Generalizable Policies","created":"2023-11-02","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},{"id":"2006.11654","title":"Counterfactually Guided Off-policy Transfer in Clinical Settings","created":"2020-06-20","cited_by_count":14},{"id":"2202.04828","title":"Learning Latent Causal Dynamics","created":"2022-02-10","cited_by_count":13},{"id":"2202.06545","title":"Provably Efficient Causal Model-Based Reinforcement Learning for Systematic Generalization","created":"2022-02-14","cited_by_count":12},{"id":"1301.6704","title":"SPUDD: Stochastic Planning using Decision Diagrams","created":"2013-01-23","cited_by_count":7},{"id":"2306.00585","title":"Causal Imitability Under Context-Specific Independence Relations","created":"2023-06-01","cited_by_count":6},{"id":"2405.07220","title":"On Discovery of Local Independence over Continuous Variables via Neural Contextual Decomposition","created":"2024-05-12","cited_by_count":4},{"id":"1301.7408","title":"Context-Specific Approximation in Probabilistic Inference","created":"2013-01-30","cited_by_count":3}],"next_cursor":null}