{"list":"other","total":60,"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":"1412.3555","title":"Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling","created":"2014-12-11","cited_by_count":2367},{"id":"1907.02893","title":"Invariant Risk Minimization","created":"2019-07-05","cited_by_count":1854},{"id":"1703.06103","title":"Modeling Relational Data with Graph Convolutional Networks","created":"2017-03-17","cited_by_count":1694},{"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":"1707.01495","title":"Hindsight Experience Replay","created":"2017-07-05","cited_by_count":1136},{"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":"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":"1805.00909","title":"Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review","created":"2018-05-02","cited_by_count":482},{"id":"2003.04960","title":"Curriculum Learning for Reinforcement Learning Domains: A Framework and Survey","created":"2020-03-10","cited_by_count":373},{"id":"2006.11287","title":"Discovering Symbolic Models from Deep Learning with Inductive Biases","created":"2020-06-19","cited_by_count":344},{"id":"1806.06920","title":"Maximum a Posteriori Policy Optimisation","created":"2018-06-14","cited_by_count":328},{"id":"1705.06366","title":"Automatic Goal Generation for Reinforcement Learning Agents","created":"2017-05-17","cited_by_count":259},{"id":"2007.01754","title":"Differentiable Causal Discovery from Interventional Data","created":"2020-07-03","cited_by_count":218},{"id":"1905.10958","title":"Explainable Reinforcement Learning Through a Causal Lens","created":"2019-05-27","cited_by_count":177},{"id":"1904.04762","title":"Active Domain Randomization","created":"2019-04-09","cited_by_count":170},{"id":"1907.02057","title":"Benchmarking Model-Based Reinforcement Learning","created":"2019-07-03","cited_by_count":162},{"id":"2201.08299","title":"Goal-Conditioned Reinforcement Learning: Problems and Solutions","created":"2022-01-20","cited_by_count":158},{"id":"1906.04477","title":"Causal Discovery with Reinforcement Learning","created":"2019-06-11","cited_by_count":145},{"id":"2011.13389","title":"Generalization in Reinforcement Learning by Soft Data Augmentation","created":"2020-11-26","cited_by_count":137},{"id":"1910.01075","title":"Learning Neural Causal Models from Unknown Interventions","created":"2019-10-02","cited_by_count":113},{"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":"2107.00644","title":"Stabilizing Deep Q-Learning with ConvNets and Vision Transformers under Data Augmentation","created":"2021-07-01","cited_by_count":105},{"id":"1910.05396","title":"Network Randomization: A Simple Technique for Generalization in Deep Reinforcement Learning","created":"2019-10-11","cited_by_count":104},{"id":"2007.02832","title":"Maximum Entropy Gain Exploration for Long Horizon Multi-goal Reinforcement Learning","created":"2020-07-06","cited_by_count":102},{"id":"1810.10093","title":"Structured Domain Randomization: Bridging the Reality Gap by Context-Aware Synthetic Data","created":"2018-10-23","cited_by_count":94},{"id":"2007.02863","title":"Counterfactual Data Augmentation using Locally Factored Dynamics","created":"2020-07-06","cited_by_count":93},{"id":"1911.01417","title":"Keeping Your Distance: Solving Sparse Reward Tasks Using Self-Balancing Shaped Rewards","created":"2019-11-04","cited_by_count":78},{"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":"2106.03443","title":"Causal Influence Detection for Improving Efficiency in Reinforcement Learning","created":"2021-06-07","cited_by_count":71},{"id":"2206.13452","title":"Causal Dynamics Learning for Task-Independent State Abstraction","created":"2022-06-27","cited_by_count":65},{"id":"1807.03480","title":"Neural Task Graphs: Generalizing to Unseen Tasks from a Single Video Demonstration","created":"2018-07-10","cited_by_count":61},{"id":"2006.06649","title":"Closed Loop Neural-Symbolic Learning via Integrating Neural Perception, Grammar Parsing, and Symbolic Reasoning","created":"2020-06-11","cited_by_count":58},{"id":"1906.04279","title":"Exploration via Hindsight Goal Generation","created":"2019-06-10","cited_by_count":54},{"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":"2007.07170","title":"Goal-Aware Prediction: Learning to Model What Matters","created":"2020-07-14","cited_by_count":45},{"id":"1609.05518","title":"Towards Deep Symbolic Reinforcement Learning","created":"2016-09-18","cited_by_count":42},{"id":"2109.02429","title":"Learning Neural Causal Models with Active Interventions","created":"2021-09-06","cited_by_count":40},{"id":"2106.14421","title":"Causal Reinforcement Learning using Observational and Interventional Data","created":"2021-06-28","cited_by_count":39},{"id":"1909.13072","title":"Regression Planning Networks","created":"2019-09-28","cited_by_count":32},{"id":"1910.01751","title":"Causal Induction from Visual Observations for Goal Directed Tasks","created":"2019-10-03","cited_by_count":31},{"id":"2203.00397","title":"A Theory of Abstraction in Reinforcement Learning","created":"2022-03-01","cited_by_count":27},{"id":"1810.11867","title":"Experimental Design for Cost-Aware Learning of Causal Graphs","created":"2018-10-28","cited_by_count":25},{"id":"1711.11560","title":"Testing Conditional Independence of Discrete Distributions","created":"2017-11-30","cited_by_count":22},{"id":"2005.11736","title":"Efficient Intervention Design for Causal Discovery with Latents","created":"2020-05-24","cited_by_count":22},{"id":"2110.00804","title":"ProTo: Program-Guided Transformer for Program-Guided Tasks","created":"2021-10-02","cited_by_count":21},{"id":"2202.05839","title":"Abstraction for Deep Reinforcement Learning","created":"2022-02-10","cited_by_count":19},{"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":"1901.08987","title":"Dynamical Isometry and a Mean Field Theory of LSTMs and GRUs","created":"2019-01-25","cited_by_count":17},{"id":"2104.10190","title":"Outcome-Driven Reinforcement Learning via Variational Inference","created":"2021-04-20","cited_by_count":17},{"id":"1804.02747","title":"Fast Conditional Independence Test for Vector Variables with Large Sample Sizes","created":"2018-04-08","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":"2002.05217","title":"Resolving Spurious Correlations in Causal Models of Environments via Interventions","created":"2020-02-12","cited_by_count":14},{"id":"2006.07549","title":"Hindsight Expectation Maximization for Goal-conditioned Reinforcement Learning","created":"2020-06-13","cited_by_count":12},{"id":"2110.14248","title":"Learning Domain Invariant Representations in Goal-conditioned Block MDPs","created":"2021-10-27","cited_by_count":12}],"next_cursor":null}