{"list":"other","total":127,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"1909.08593","title":"Fine-Tuning Language Models from Human Preferences","created":"2019-09-18","cited_by_count":2150},{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920},{"id":"2006.04779","title":"Conservative Q-Learning for Offline Reinforcement Learning","created":"2020-06-08","cited_by_count":1809},{"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":"1812.02900","title":"Off-Policy Deep Reinforcement Learning without Exploration","created":"2018-12-07","cited_by_count":1241},{"id":"1910.10897","title":"Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning","created":"2019-10-24","cited_by_count":1204},{"id":"1705.05363","title":"Curiosity-driven Exploration by Self-supervised Prediction","created":"2017-05-15","cited_by_count":1194},{"id":"1810.12894","title":"Exploration by Random Network Distillation","created":"2018-10-30","cited_by_count":993},{"id":"1705.10528","title":"Constrained Policy Optimization","created":"2017-05-30","cited_by_count":983},{"id":"1703.06856","title":"Counterfactual Fairness","created":"2017-03-20","cited_by_count":804},{"id":"1705.08926","title":"Counterfactual Multi-Agent Policy Gradients","created":"2017-05-24","cited_by_count":751},{"id":"1910.07113","title":"Solving Rubik's Cube with a Robot Hand","created":"2019-10-16","cited_by_count":734},{"id":"1909.12271","title":"RLBench: The Robot Learning Benchmark & Learning Environment","created":"2019-09-26","cited_by_count":689},{"id":"1710.06537","title":"Sim-to-Real Transfer of Robotic Control with Dynamics Randomization","created":"2017-10-18","cited_by_count":672},{"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":"2209.14375","title":"Improving alignment of dialogue agents via targeted human judgements","created":"2022-09-28","cited_by_count":531},{"id":"1611.02779","title":"RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning","created":"2016-11-09","cited_by_count":503},{"id":"1912.01588","title":"Leveraging Procedural Generation to Benchmark Reinforcement Learning","created":"2019-12-03","cited_by_count":483},{"id":"2006.10742","title":"Learning Invariant Representations for Reinforcement Learning without Reconstruction","created":"2020-06-18","cited_by_count":436},{"id":"2002.11949","title":"Unbiased Scene Graph Generation from Biased Training","created":"2020-02-27","cited_by_count":356},{"id":"1512.01629","title":"Risk-Constrained Reinforcement Learning with Percentile Risk Criteria","created":"2015-12-05","cited_by_count":337},{"id":"2012.13490","title":"Towards Continual Reinforcement Learning: A Review and Perspectives","created":"2020-12-25","cited_by_count":274},{"id":"1711.00832","title":"A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning","created":"2017-11-02","cited_by_count":268},{"id":"2009.07888","title":"Transfer Learning in Deep Reinforcement Learning: A Survey","created":"2020-09-16","cited_by_count":265},{"id":"1306.0940","title":"(More) Efficient Reinforcement Learning via Posterior Sampling","created":"2013-06-04","cited_by_count":233},{"id":"1707.04175","title":"Distral: Robust Multitask Reinforcement Learning","created":"2017-07-13","cited_by_count":233},{"id":"1502.02259","title":"Contextual Markov Decision Processes","created":"2015-02-08","cited_by_count":220},{"id":"2007.01754","title":"Differentiable Causal Discovery from Interventional Data","created":"2020-07-03","cited_by_count":218},{"id":"2103.02582","title":"D'ya like DAGs? A Survey on Structure Learning and Causal Discovery","created":"2021-03-03","cited_by_count":211},{"id":"1803.04383","title":"Delayed Impact of Fair Machine Learning","created":"2018-03-12","cited_by_count":184},{"id":"2205.10330","title":"A Review of Safe Reinforcement Learning: Methods, Theory and Applications","created":"2022-05-20","cited_by_count":181},{"id":"1511.06342","title":"Actor-Mimic: Deep Multitask and Transfer Reinforcement Learning","created":"2015-11-19","cited_by_count":178},{"id":"2109.00725","title":"Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyond","created":"2021-09-02","cited_by_count":178},{"id":"1905.10958","title":"Explainable Reinforcement Learning Through a Causal Lens","created":"2019-05-27","cited_by_count":177},{"id":"1804.06893","title":"A Study on Overfitting in Deep Reinforcement Learning","created":"2018-04-18","cited_by_count":174},{"id":"1907.02057","title":"Benchmarking Model-Based Reinforcement Learning","created":"2019-07-03","cited_by_count":162},{"id":"1805.09801","title":"Meta-Gradient Reinforcement Learning","created":"2018-05-24","cited_by_count":159},{"id":"2104.07876","title":"Deep Stable Learning for Out-Of-Distribution Generalization","created":"2021-04-16","cited_by_count":153},{"id":"1707.08475","title":"DARLA: Improving Zero-Shot Transfer in Reinforcement Learning","created":"2017-07-26","cited_by_count":149},{"id":"1906.04477","title":"Causal Discovery with Reinforcement Learning","created":"2019-06-11","cited_by_count":145},{"id":"1711.00138","title":"Visualizing and Understanding Atari Agents","created":"2017-10-31","cited_by_count":141},{"id":"2005.06247","title":"Explainable Reinforcement Learning: A Survey","created":"2020-05-13","cited_by_count":141},{"id":"1910.03016","title":"Is a Good Representation Sufficient for Sample Efficient Reinforcement Learning?","created":"2019-10-07","cited_by_count":140},{"id":"1609.08816","title":"Identifying Causal Effects With Proxy Variables of an Unmeasured Confounder","created":"2016-09-28","cited_by_count":139},{"id":"1802.07245","title":"Meta-Reinforcement Learning of Structured Exploration Strategies","created":"2018-02-20","cited_by_count":130},{"id":"2105.06067","title":"Causal Intervention for Leveraging Popularity Bias in Recommendation","created":"2021-05-13","cited_by_count":116},{"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":"1908.04734","title":"Reward Tampering Problems and Solutions in Reinforcement Learning: A Causal Influence Diagram Perspective","created":"2019-08-13","cited_by_count":108},{"id":"2002.12204","title":"Visual Commonsense R-CNN","created":"2020-02-27","cited_by_count":106},{"id":"2003.06016","title":"Invariant Causal Prediction for Block MDPs","created":"2020-03-12","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":"1606.03203","title":"Causal Bandits: Learning Good Interventions via Causal Inference","created":"2016-06-10","cited_by_count":101},{"id":"2008.06693","title":"Explainability in Deep Reinforcement Learning","created":"2020-08-15","cited_by_count":97},{"id":"2007.02863","title":"Counterfactual Data Augmentation using Locally Factored Dynamics","created":"2020-07-06","cited_by_count":93},{"id":"1806.07937","title":"A Dissection of Overfitting and Generalization in Continuous Reinforcement Learning","created":"2018-06-20","cited_by_count":87},{"id":"1811.06272","title":"Woulda, Coulda, Shoulda: Counterfactually-Guided Policy Search","created":"2018-11-15","cited_by_count":82},{"id":"1906.02500","title":"Towards Interpretable Reinforcement Learning Using Attention Augmented Agents","created":"2019-06-06","cited_by_count":82},{"id":"2102.10330","title":"Decoupling Value and Policy for Generalization in Reinforcement Learning","created":"2021-02-20","cited_by_count":82},{"id":"2010.10814","title":"Improving Generalization in Reinforcement Learning with Mixture Regularization","created":"2020-10-21","cited_by_count":81},{"id":"2108.08782","title":"Causal Attention for Unbiased Visual Recognition","created":"2021-08-19","cited_by_count":80},{"id":"1605.08179","title":"Discovering Causal Signals in Images","created":"2016-05-26","cited_by_count":79},{"id":"2003.11881","title":"An empirical investigation of the challenges of real-world reinforcement learning","created":"2020-03-24","cited_by_count":77},{"id":"2109.03795","title":"Desiderata for Representation Learning: A Causal Perspective","created":"2021-09-08","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":"2010.02637","title":"Weakly Supervised Disentangled Generative Causal Representation Learning","created":"2020-10-06","cited_by_count":68},{"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":"2011.09464","title":"Counterfactual Credit Assignment in Model-Free Reinforcement Learning","created":"2020-11-18","cited_by_count":64},{"id":"2003.05623","title":"Off-policy Policy Evaluation For Sequential Decisions Under Unobserved Confounding","created":"2020-03-12","cited_by_count":61},{"id":"2010.11300","title":"How Do Fair Decisions Fare in Long-term Qualification?","created":"2020-10-21","cited_by_count":60},{"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":"1901.08568","title":"Algorithms for Fairness in Sequential Decision Making","created":"2019-01-24","cited_by_count":56},{"id":"2206.02013","title":"Causal Discovery in Heterogeneous Environments Under the Sparse Mechanism Shift Hypothesis","created":"2022-06-04","cited_by_count":55},{"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":"2107.00848","title":"Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learning","created":"2021-07-02","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":"1909.09141","title":"Causal Modeling for Fairness in Dynamical Systems","created":"2019-09-18","cited_by_count":47},{"id":"2208.12397","title":"Causal Inference in Recommender Systems: A Survey and Future Directions","created":"2022-08-26","cited_by_count":44},{"id":"2210.11287","title":"MoCoDA: Model-based Counterfactual Data Augmentation","created":"2022-10-20","cited_by_count":44},{"id":"2007.13893","title":"Off-policy Evaluation in Infinite-Horizon Reinforcement Learning with Latent Confounders","created":"2020-07-27","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":"1701.02789","title":"Identifying Best Interventions through Online Importance Sampling","created":"2017-01-10","cited_by_count":39},{"id":"2106.14421","title":"Causal Reinforcement Learning using Observational and Interventional Data","created":"2021-06-28","cited_by_count":39},{"id":"2012.07058","title":"Budgeted and Non-budgeted Causal Bandits","created":"2020-12-13","cited_by_count":38},{"id":"2106.02988","title":"Causal Bandits with Unknown Graph Structure","created":"2021-06-05","cited_by_count":37},{"id":"2107.02776","title":"Counterfactual Explanations in Sequential Decision Making Under Uncertainty","created":"2021-07-06","cited_by_count":37},{"id":"1812.10576","title":"Deconfounding Reinforcement Learning in Observational Settings","created":"2018-12-26","cited_by_count":36},{"id":"2102.02926","title":"Alchemy: A benchmark and analysis toolkit for meta-reinforcement learning agents","created":"2021-02-04","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":"2109.09180","title":"Lifelong Robotic Reinforcement Learning by Retaining Experiences","created":"2021-09-19","cited_by_count":34},{"id":"2207.09081","title":"Generalizing Goal-Conditioned Reinforcement Learning with Variational Causal Reasoning","created":"2022-07-19","cited_by_count":34}],"next_cursor":"100"}