{"list":"other","total":79,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"2212.06817","title":"RT-1: Robotics Transformer for Real-World Control at Scale","created":"2022-12-13","cited_by_count":2061},{"id":"2006.04779","title":"Conservative Q-Learning for Offline Reinforcement Learning","created":"2020-06-08","cited_by_count":1809},{"id":"2202.12837","title":"Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?","created":"2022-02-25","cited_by_count":1434},{"id":"1812.02900","title":"Off-Policy Deep Reinforcement Learning without Exploration","created":"2018-12-07","cited_by_count":1241},{"id":"2111.02080","title":"An Explanation of In-context Learning as Implicit Bayesian Inference","created":"2021-11-03","cited_by_count":938},{"id":"2308.10144","title":"ExpeL: LLM Agents Are Experiential Learners","created":"2023-08-20","cited_by_count":876},{"id":"1906.00949","title":"Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction","created":"2019-06-03","cited_by_count":840},{"id":"2205.06175","title":"A Generalist Agent","created":"2022-05-12","cited_by_count":808},{"id":"1911.11361","title":"Behavior Regularized Offline Reinforcement Learning","created":"2019-11-26","cited_by_count":662},{"id":"1710.10345","title":"The Implicit Bias of Gradient Descent on Separable Data","created":"2017-10-27","cited_by_count":655},{"id":"1611.02779","title":"RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning","created":"2016-11-09","cited_by_count":503},{"id":"1707.02038","title":"A Tutorial on Thompson Sampling","created":"2017-07-07","cited_by_count":433},{"id":"1903.08254","title":"Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables","created":"2019-03-19","cited_by_count":389},{"id":"1611.05763","title":"Learning to reinforcement learn","created":"2016-11-17","cited_by_count":377},{"id":"2102.08363","title":"COMBO: Conservative Offline Model-Based Policy Optimization","created":"2021-02-16","cited_by_count":370},{"id":"2112.10510","title":"Transformers Can Do Bayesian Inference","created":"2021-12-20","cited_by_count":360},{"id":"1704.00445","title":"On Kernelized Multi-armed Bandits","created":"2017-04-03","cited_by_count":352},{"id":"2206.11251","title":"Behavior Transformers: Cloning $k$ modes with one stone","created":"2022-06-22","cited_by_count":304},{"id":"1803.11347","title":"Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learning","created":"2018-03-30","cited_by_count":276},{"id":"2301.07067","title":"Transformers as Algorithms: Generalization and Stability in In-context Learning","created":"2023-01-17","cited_by_count":222},{"id":"1910.08348","title":"VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning","created":"2019-10-18","cited_by_count":217},{"id":"2002.08396","title":"Keep Doing What Worked: Behavioral Modelling Priors for Offline Reinforcement Learning","created":"2020-02-19","cited_by_count":215},{"id":"1811.12560","title":"An Introduction to Deep Reinforcement Learning","created":"2018-11-30","cited_by_count":206},{"id":"1905.10389","title":"Reinforcement Learning in Feature Space: Matrix Bandit, Kernels, and Regret Bound","created":"2019-05-24","cited_by_count":201},{"id":"2307.04721","title":"Large Language Models as General Pattern Machines","created":"2023-07-10","cited_by_count":197},{"id":"2210.14215","title":"In-context Reinforcement Learning with Algorithm Distillation","created":"2022-10-25","cited_by_count":190},{"id":"2205.10330","title":"A Review of Safe Reinforcement Learning: Methods, Theory and Applications","created":"2022-05-20","cited_by_count":181},{"id":"1309.6869","title":"Finite-Time Analysis of Kernelised Contextual Bandits","created":"2013-09-26","cited_by_count":177},{"id":"1802.09127","title":"Deep Bayesian Bandits Showdown: An Empirical Comparison of Bayesian Deep Networks for Thompson Sampling","created":"2018-02-26","cited_by_count":169},{"id":"2003.02189","title":"Exploration-Exploitation in Constrained MDPs","created":"2020-03-04","cited_by_count":149},{"id":"2209.04881","title":"On The Computational Complexity of Self-Attention","created":"2022-09-11","cited_by_count":139},{"id":"2306.14892","title":"Supervised Pretraining Can Learn In-Context Reinforcement Learning","created":"2023-06-26","cited_by_count":139},{"id":"1802.07245","title":"Meta-Reinforcement Learning of Structured Exploration Strategies","created":"2018-02-20","cited_by_count":130},{"id":"2305.15525","title":"Large Language Models are Few-Shot Health Learners","created":"2023-05-24","cited_by_count":118},{"id":"2308.13111","title":"Bayesian Low-rank Adaptation for Large Language Models","created":"2023-08-24","cited_by_count":115},{"id":"2303.03982","title":"Structured State Space Models for In-Context Reinforcement Learning","created":"2023-03-07","cited_by_count":111},{"id":"1810.06784","title":"ProMP: Proximal Meta-Policy Search","created":"2018-10-16","cited_by_count":91},{"id":"2209.10342","title":"Partially Observable Markov Decision Processes in Robotics: A Survey","created":"2022-09-21","cited_by_count":86},{"id":"1605.05362","title":"Yelp Dataset Challenge: Review Rating Prediction","created":"2016-05-17","cited_by_count":84},{"id":"2205.13703","title":"Why So Pessimistic? Estimating Uncertainties for Offline RL through Ensembles, and Why Their Independence Matters","created":"2022-05-27","cited_by_count":76},{"id":"2206.01079","title":"When does return-conditioned supervised learning work for offline reinforcement learning?","created":"2022-06-02","cited_by_count":76},{"id":"1806.01830","title":"Relational Deep Reinforcement Learning","created":"2018-06-05","cited_by_count":73},{"id":"2305.14292","title":"WikiChat: Stopping the Hallucination of Large Language Model Chatbots by Few-Shot Grounding on Wikipedia","created":"2023-05-23","cited_by_count":67},{"id":"2110.08118","title":"Few-Shot Bot: Prompt-Based Learning for Dialogue Systems","created":"2021-10-15","cited_by_count":64},{"id":"2007.00953","title":"Gamification of Pure Exploration for Linear Bandits","created":"2020-07-02","cited_by_count":63},{"id":"1405.4758","title":"Lipschitz Bandits: Regret Lower Bounds and Optimal Algorithms","created":"2014-05-19","cited_by_count":60},{"id":"2008.02790","title":"Decoupling Exploration and Exploitation for Meta-Reinforcement Learning without Sacrifices","created":"2020-08-06","cited_by_count":59},{"id":"1901.02470","title":"Bilinear Bandits with Low-rank Structure","created":"2019-01-08","cited_by_count":55},{"id":"2010.06531","title":"Impact of Representation Learning in Linear Bandits","created":"2020-10-13","cited_by_count":52},{"id":"1811.11880","title":"Predicting the Computational Cost of Deep Learning Models","created":"2018-11-28","cited_by_count":49},{"id":"2006.02948","title":"Low-Rank Generalized Linear Bandit Problems","created":"2020-06-04","cited_by_count":49},{"id":"2309.17382","title":"Reason for Future, Act for Now: A Principled Framework for Autonomous LLM Agents with Provable Sample Efficiency","created":"2023-09-29","cited_by_count":46},{"id":"2006.08714","title":"Latent Bandits Revisited","created":"2020-06-15","cited_by_count":44},{"id":"1902.00470","title":"An Information-Theoretic Approach to Minimax Regret in Partial Monitoring","created":"2019-02-01","cited_by_count":42},{"id":"1705.03071","title":"Geometry of Optimization and Implicit Regularization in Deep Learning","created":"2017-05-08","cited_by_count":39},{"id":"2111.06929","title":"Hierarchical Bayesian Bandits","created":"2021-11-12","cited_by_count":35},{"id":"2102.04168","title":"Provable Model-based Nonlinear Bandit and Reinforcement Learning: Shelve Optimism, Embrace Virtual Curvature","created":"2021-02-08","cited_by_count":32},{"id":"1712.04644","title":"Stochastic Low-Rank Bandits","created":"2017-12-13","cited_by_count":28},{"id":"2002.00232","title":"Thompson Sampling Algorithms for Mean-Variance Bandits","created":"2020-02-01","cited_by_count":27},{"id":"1509.06841","title":"One-Shot Learning of Manipulation Skills with Online Dynamics Adaptation and Neural Network Priors","created":"2015-09-23","cited_by_count":26},{"id":"2312.13327","title":"In-Context Reinforcement Learning for Variable Action Spaces","created":"2023-12-20","cited_by_count":24},{"id":"1301.1722","title":"Linear Bandits in High Dimension and Recommendation Systems","created":"2013-01-08","cited_by_count":22},{"id":"2212.04590","title":"Learning Options via Compression","created":"2022-12-08","cited_by_count":22},{"id":"2401.07298","title":"Efficient Frameworks for Generalized Low-Rank Matrix Bandit Problems","created":"2024-01-14","cited_by_count":20},{"id":"2202.01454","title":"Deep Hierarchy in Bandits","created":"2022-02-03","cited_by_count":19},{"id":"2203.15664","title":"Nearly Minimax Algorithms for Linear Bandits with Shared Representation","created":"2022-03-29","cited_by_count":16},{"id":"2204.14081","title":"Few-shot learning for medical text: A systematic review","created":"2022-04-21","cited_by_count":13},{"id":"1907.04964","title":"A Model-based Approach for Sample-efficient Multi-task Reinforcement Learning","created":"2019-07-11","cited_by_count":12},{"id":"2301.07040","title":"Optimal Algorithms for Latent Bandits with Cluster Structure","created":"2023-01-17","cited_by_count":12},{"id":"2212.04720","title":"Multi-Task Off-Policy Learning from Bandit Feedback","created":"2022-12-09","cited_by_count":9},{"id":"2302.04441","title":"Multi-task Representation Learning for Pure Exploration in Linear Bandits","created":"2023-02-09","cited_by_count":6},{"id":"2311.00327","title":"Multi-task Representation Learning for Pure Exploration in Bilinear Bandits","created":"2023-11-01","cited_by_count":5},{"id":"2002.09971","title":"Rapidly Personalizing Mobile Health Treatment Policies with Limited Data","created":"2020-02-23","cited_by_count":4},{"id":"2210.03528","title":"Tractable Optimality in Episodic Latent MABs","created":"2022-10-05","cited_by_count":3},{"id":"2401.00031","title":"Self-supervised Pretraining for Decision Foundation Model: Formulation, Pipeline and Challenges","created":"2023-12-29","cited_by_count":2}],"next_cursor":null}