{"list":"other","total":61,"rows":[{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1312.6114","title":"Auto-Encoding Variational Bayes","created":"2013-12-20","cited_by_count":4053},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"1509.02971","title":"Continuous control with deep reinforcement learning","created":"2015-09-09","cited_by_count":3407},{"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":"1811.04551","title":"Learning Latent Dynamics for Planning from Pixels","created":"2018-11-12","cited_by_count":1264},{"id":"1811.12359","title":"Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations","created":"2018-11-29","cited_by_count":941},{"id":"1504.00702","title":"End-to-End Training of Deep Visuomotor Policies","created":"2015-04-02","cited_by_count":875},{"id":"1802.05983","title":"Disentangling by Factorising","created":"2018-02-16","cited_by_count":616},{"id":"1907.04809","title":"Variational Autoencoders and Nonlinear ICA: A Unifying Framework","created":"2019-07-10","cited_by_count":503},{"id":"2006.10742","title":"Learning Invariant Representations for Reinforcement Learning without Reconstruction","created":"2020-06-18","cited_by_count":436},{"id":"2203.04955","title":"Temporal Difference Learning for Model Predictive Control","created":"2022-03-09","cited_by_count":397},{"id":"2306.13831","title":"Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Tasks","created":"2023-06-24","cited_by_count":327},{"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":"1805.08651","title":"Nonlinear ICA Using Auxiliary Variables and Generalized Contrastive Learning","created":"2018-05-22","cited_by_count":282},{"id":"1605.06336","title":"Unsupervised Feature Extraction by Time-Contrastive Learning and Nonlinear ICA","created":"2016-05-20","cited_by_count":273},{"id":"2002.02886","title":"Weakly-Supervised Disentanglement Without Compromises","created":"2020-02-07","cited_by_count":239},{"id":"1906.02736","title":"DeepMDP: Learning Continuous Latent Space Models for Representation Learning","created":"2019-06-06","cited_by_count":207},{"id":"2107.10098","title":"Disentanglement via Mechanism Sparsity Regularization: A New Principle for Nonlinear ICA","created":"2021-07-21","cited_by_count":160},{"id":"1707.08475","title":"DARLA: Improving Zero-Shot Transfer in Reinforcement Learning","created":"2017-07-26","cited_by_count":149},{"id":"2209.11924","title":"Interventional Causal Representation Learning","created":"2022-09-24","cited_by_count":142},{"id":"2202.03169","title":"CITRIS: Causal Identifiability from Temporal Intervened Sequences","created":"2022-02-07","cited_by_count":133},{"id":"2007.10930","title":"Towards Nonlinear Disentanglement in Natural Data with Temporal Sparse Coding","created":"2020-07-21","cited_by_count":122},{"id":"2306.00542","title":"Nonparametric Identifiability of Causal Representations from Unknown Interventions","created":"2023-06-01","cited_by_count":106},{"id":"2002.11537","title":"ICE-BeeM: Identifiable Conditional Energy-Based Deep Models Based on Nonlinear ICA","created":"2020-02-26","cited_by_count":102},{"id":"2007.02863","title":"Counterfactual Data Augmentation using Locally Factored Dynamics","created":"2020-07-06","cited_by_count":93},{"id":"2306.02235","title":"Learning Linear Causal Representations from Interventions under General Nonlinear Mixing","created":"2023-06-04","cited_by_count":92},{"id":"2211.16467","title":"Linear Causal Disentanglement via Interventions","created":"2022-11-29","cited_by_count":84},{"id":"2307.06250","title":"Identifiability Guarantees for Causal Disentanglement from Soft Interventions","created":"2023-07-12","cited_by_count":84},{"id":"2107.10483","title":"Efficient Neural Causal Discovery without Acyclicity Constraints","created":"2021-07-22","cited_by_count":82},{"id":"2106.03443","title":"Causal Influence Detection for Improving Efficiency in Reinforcement Learning","created":"2021-06-07","cited_by_count":71},{"id":"2206.15477","title":"Denoised MDPs: Learning World Models Better Than the World Itself","created":"2022-06-30","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":"2007.12401","title":"Predictive Information Accelerates Learning in RL","created":"2020-07-24","cited_by_count":56},{"id":"2106.07156","title":"Temporal Predictive Coding For Model-Based Planning In Latent Space","created":"2021-06-14","cited_by_count":55},{"id":"2107.00848","title":"Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learning","created":"2021-07-02","cited_by_count":53},{"id":"2206.06169","title":"Causal Representation Learning for Instantaneous and Temporal Effects in Interactive Systems","created":"2022-06-13","cited_by_count":51},{"id":"2303.16535","title":"Nonlinear Independent Component Analysis for Principled Disentanglement in Unsupervised Deep Learning","created":"2023-03-29","cited_by_count":48},{"id":"2207.08229","title":"Guaranteed Discovery of Control-Endogenous Latent States with Multi-Step Inverse Models","created":"2022-07-17","cited_by_count":45},{"id":"2106.04379","title":"Learning Markov State Abstractions for Deep Reinforcement Learning","created":"2021-06-08","cited_by_count":44},{"id":"2210.11287","title":"MoCoDA: Model-based Counterfactual Data Augmentation","created":"2022-10-20","cited_by_count":44},{"id":"1403.3741","title":"Near-optimal Reinforcement Learning in Factored MDPs","created":"2014-03-15","cited_by_count":41},{"id":"2401.04890","title":"Nonparametric Partial Disentanglement via Mechanism Sparsity: Sparse Actions, Interventions and Sparse Temporal Dependencies","created":"2024-01-10","cited_by_count":41},{"id":"2305.18378","title":"Disentanglement via Latent Quantization","created":"2023-05-28","cited_by_count":40},{"id":"2306.09643","title":"BISCUIT: Causal Representation Learning from Binary Interactions","created":"2023-06-16","cited_by_count":38},{"id":"2310.15450","title":"General Identifiability and Achievability for Causal Representation Learning","created":"2023-10-24","cited_by_count":34},{"id":"2305.14133","title":"Conditional Mutual Information for Disentangled Representations in Reinforcement Learning","created":"2023-05-23","cited_by_count":27},{"id":"2210.00364","title":"DCI-ES: An Extended Disentanglement Framework with Connections to Identifiability","created":"2022-10-01","cited_by_count":23},{"id":"2306.06561","title":"Learning World Models with Identifiable Factorization","created":"2023-06-11","cited_by_count":23},{"id":"2207.05480","title":"Temporal Disentanglement of Representations for Improved Generalisation in Reinforcement Learning","created":"2022-07-12","cited_by_count":19},{"id":"1802.09484","title":"Disentangling the independently controllable factors of variation by interacting with the world","created":"2018-02-26","cited_by_count":16},{"id":"2206.11131","title":"Variational Causal Dynamics: Discovering Modular World Models from Interventions","created":"2022-06-22","cited_by_count":16},{"id":"2006.13405","title":"Towards Minimax Optimal Reinforcement Learning in Factored Markov Decision Processes","created":"2020-06-24","cited_by_count":13},{"id":"2404.10282","title":"Tripod: Three Complementary Inductive Biases for Disentangled Representation Learning","created":"2024-04-16","cited_by_count":13},{"id":"2410.18416","title":"SkiLD: Unsupervised Skill Discovery Guided by Factor Interactions","created":"2024-10-24","cited_by_count":9},{"id":"2310.08702","title":"ELDEN: Exploration via Local Dependencies","created":"2023-10-12","cited_by_count":8},{"id":"1301.3869","title":"Policy Iteration for Factored MDPs","created":"2013-01-16","cited_by_count":6},{"id":"2306.09509","title":"Granger Causal Interaction Skill Chains","created":"2023-06-15","cited_by_count":6},{"id":"2409.18330","title":"DMC-VB: A Benchmark for Representation Learning for Control with Visual Distractors","created":"2024-09-26","cited_by_count":5},{"id":"2406.15850","title":"Learning Abstract World Model for Value-preserving Planning with Options","created":"2024-06-22","cited_by_count":4},{"id":"2002.02302","title":"Reinforcement Learning in Factored MDPs: Oracle-Efficient Algorithms and Tighter Regret Bounds for the Non-Episodic Setting","created":"2020-02-06","cited_by_count":3}],"next_cursor":null}