{"list":"other","total":57,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2106.01345","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","created":"2021-06-02","cited_by_count":1546},{"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":"2004.07219","title":"D4RL: Datasets for Deep Data-Driven Reinforcement Learning","created":"2020-04-15","cited_by_count":1427},{"id":"2203.14465","title":"STaR: Bootstrapping Reasoning With Reasoning","created":"2022-03-28","cited_by_count":940},{"id":"2112.00114","title":"Show Your Work: Scratchpads for Intermediate Computation with Language Models","created":"2021-11-30","cited_by_count":886},{"id":"1712.01815","title":"Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm","created":"2017-12-05","cited_by_count":734},{"id":"1705.04146","title":"Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problems","created":"2017-05-11","cited_by_count":650},{"id":"2106.02039","title":"Offline Reinforcement Learning as One Big Sequence Modeling Problem","created":"2021-06-03","cited_by_count":644},{"id":"2010.11251","title":"Learning Quadrupedal Locomotion over Challenging Terrain","created":"2020-10-21","cited_by_count":604},{"id":"1703.05449","title":"Minimax Regret Bounds for Reinforcement Learning","created":"2017-03-16","cited_by_count":503},{"id":"1912.01588","title":"Leveraging Procedural Generation to Benchmark Reinforcement Learning","created":"2019-12-03","cited_by_count":483},{"id":"2109.00137","title":"Implicit Behavioral Cloning","created":"2021-09-01","cited_by_count":452},{"id":"2006.10742","title":"Learning Invariant Representations for Reinforcement Learning without Reconstruction","created":"2020-06-18","cited_by_count":436},{"id":"1611.05397","title":"Reinforcement Learning with Unsupervised Auxiliary Tasks","created":"2016-11-16","cited_by_count":404},{"id":"1912.12294","title":"Learning by Cheating","created":"2019-12-27","cited_by_count":383},{"id":"1906.02361","title":"Explain Yourself! Leveraging Language Models for Commonsense Reasoning","created":"2019-06-06","cited_by_count":367},{"id":"1812.02341","title":"Quantifying Generalization in Reinforcement Learning","created":"2018-12-06","cited_by_count":352},{"id":"1910.06764","title":"Stabilizing Transformers for Reinforcement Learning","created":"2019-10-13","cited_by_count":270},{"id":"2002.05867","title":"Transformers as Soft Reasoners over Language","created":"2020-02-14","cited_by_count":270},{"id":"1709.06009","title":"Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents","created":"2017-09-18","cited_by_count":269},{"id":"1402.0555","title":"Taming the Monster: A Fast and Simple Algorithm for Contextual Bandits","created":"2014-02-04","cited_by_count":201},{"id":"1611.03673","title":"Learning to Navigate in Complex Environments","created":"2016-11-11","cited_by_count":198},{"id":"2202.05607","title":"Online Decision Transformer","created":"2022-02-11","cited_by_count":196},{"id":"1703.07710","title":"Unifying PAC and Regret: Uniform PAC Bounds for Episodic Reinforcement Learning","created":"2017-03-22","cited_by_count":176},{"id":"1804.06893","title":"A Study on Overfitting in Deep Reinforcement Learning","created":"2018-04-18","cited_by_count":174},{"id":"2010.13611","title":"OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement Learning","created":"2020-10-26","cited_by_count":166},{"id":"1906.05838","title":"Goal-conditioned Imitation Learning","created":"2019-06-13","cited_by_count":162},{"id":"1602.02867","title":"Value Iteration Networks","created":"2016-02-09","cited_by_count":160},{"id":"2006.00979","title":"Acme: A Research Framework for Distributed Reinforcement Learning","created":"2020-06-01","cited_by_count":146},{"id":"1802.09564","title":"Reinforcement and Imitation Learning for Diverse Visuomotor Skills","created":"2018-02-26","cited_by_count":126},{"id":"1810.00123","title":"Generalization and Regularization in DQN","created":"2018-09-29","cited_by_count":118},{"id":"2111.10364","title":"Generalized Decision Transformer for Offline Hindsight Information Matching","created":"2021-11-19","cited_by_count":106},{"id":"1910.05396","title":"Network Randomization: A Simple Technique for Generalization in Deep Reinforcement Learning","created":"2019-10-11","cited_by_count":104},{"id":"1511.06279","title":"Neural Programmer-Interpreters","created":"2015-11-19","cited_by_count":101},{"id":"1609.05521","title":"Playing FPS Games with Deep Reinforcement Learning","created":"2016-09-18","cited_by_count":95},{"id":"2102.05815","title":"Representation Matters: Offline Pretraining for Sequential Decision Making","created":"2021-02-11","cited_by_count":91},{"id":"1803.00590","title":"Hierarchical Imitation and Reinforcement Learning","created":"2018-03-01","cited_by_count":88},{"id":"1911.05321","title":"IRIS: Implicit Reinforcement without Interaction at Scale for Learning Control from Offline Robot Manipulation Data","created":"2019-11-13","cited_by_count":86},{"id":"1507.04296","title":"Massively Parallel Methods for Deep Reinforcement Learning","created":"2015-07-15","cited_by_count":82},{"id":"2201.12122","title":"Can Wikipedia Help Offline Reinforcement Learning?","created":"2022-01-28","cited_by_count":77},{"id":"1710.01813","title":"Neural Task Programming: Learning to Generalize Across Hierarchical Tasks","created":"2017-10-04","cited_by_count":76},{"id":"2107.08829","title":"Visual Adversarial Imitation Learning using Variational Models","created":"2021-07-16","cited_by_count":42},{"id":"2002.10544","title":"Provable Representation Learning for Imitation Learning via Bi-level Optimization","created":"2020-02-24","cited_by_count":41},{"id":"2110.14770","title":"TRAIL: Near-Optimal Imitation Learning with Suboptimal Data","created":"2021-10-27","cited_by_count":39},{"id":"2107.08981","title":"Hierarchical Few-Shot Imitation with Skill Transition Models","created":"2021-07-19","cited_by_count":37},{"id":"2112.03753","title":"Tell me why! Explanations support learning relational and causal structure","created":"2021-12-07","cited_by_count":36},{"id":"2105.12272","title":"Provable Representation Learning for Imitation with Contrastive Fourier Features","created":"2021-05-26","cited_by_count":34},{"id":"2109.13006","title":"RuleBert: Teaching Soft Rules to Pre-trained Language Models","created":"2021-09-24","cited_by_count":25},{"id":"2006.06609","title":"Leap-Of-Thought: Teaching Pre-Trained Models to Systematically Reason Over Implicit Knowledge","created":"2020-06-11","cited_by_count":24},{"id":"2203.01983","title":"Implicit Kinematic Policies: Unifying Joint and Cartesian Action Spaces in End-to-End Robot Learning","created":"2022-03-03","cited_by_count":15},{"id":"1509.03044","title":"Recurrent Reinforcement Learning: A Hybrid Approach","created":"2015-09-10","cited_by_count":13},{"id":"2109.07578","title":"Multi-Task Learning with Sequence-Conditioned Transporter Networks","created":"2021-09-15","cited_by_count":8}],"next_cursor":null}