{"list":"other","total":144,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"1509.02971","title":"Continuous control with deep reinforcement learning","created":"2015-09-09","cited_by_count":3407},{"id":"1312.5602","title":"Playing Atari with Deep Reinforcement Learning","created":"2013-12-19","cited_by_count":3274},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920},{"id":"1901.02860","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","created":"2019-01-09","cited_by_count":1850},{"id":"2106.01345","title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","created":"2021-06-02","cited_by_count":1546},{"id":"1803.10122","title":"World Models","created":"2018-03-27","cited_by_count":1513},{"id":"1806.01261","title":"Relational inductive biases, deep learning, and graph networks","created":"2018-06-04","cited_by_count":1360},{"id":"1904.01201","title":"Habitat: A Platform for Embodied AI Research","created":"2019-04-02","cited_by_count":1191},{"id":"2101.01169","title":"Transformers in Vision: A Survey","created":"2021-01-04","cited_by_count":1013},{"id":"2010.02193","title":"Mastering Atari with Discrete World Models","created":"2020-10-05","cited_by_count":1007},{"id":"1906.02691","title":"An Introduction to Variational Autoencoders","created":"2019-06-06","cited_by_count":1000},{"id":"2006.15055","title":"Object-Centric Learning with Slot Attention","created":"2020-06-26","cited_by_count":876},{"id":"2106.03106","title":"Uformer: A General U-Shaped Transformer for Image Restoration","created":"2021-06-06","cited_by_count":866},{"id":"2004.04136","title":"CURL: Contrastive Unsupervised Representations for Reinforcement Learning","created":"2020-04-08","cited_by_count":760},{"id":"1806.10293","title":"QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation","created":"2018-06-27","cited_by_count":743},{"id":"1910.07113","title":"Solving Rubik's Cube with a Robot Hand","created":"2019-10-16","cited_by_count":734},{"id":"2002.00444","title":"Deep Reinforcement Learning for Autonomous Driving: A Survey","created":"2020-02-02","cited_by_count":721},{"id":"2301.00808","title":"ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders","created":"2023-01-02","cited_by_count":712},{"id":"2012.09699","title":"A Generalization of Transformer Networks to Graphs","created":"2020-12-17","cited_by_count":661},{"id":"2106.02039","title":"Offline Reinforcement Learning as One Big Sequence Modeling Problem","created":"2021-06-03","cited_by_count":644},{"id":"2107.14795","title":"Perceiver IO: A General Architecture for Structured Inputs & Outputs","created":"2021-07-30","cited_by_count":629},{"id":"2012.09838","title":"Transformer Interpretability Beyond Attention Visualization","created":"2020-12-17","cited_by_count":627},{"id":"1907.00235","title":"Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting","created":"2019-06-29","cited_by_count":607},{"id":"1605.06676","title":"Learning to Communicate with Deep Multi-Agent Reinforcement Learning","created":"2016-05-21","cited_by_count":575},{"id":"2103.10697","title":"ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases","created":"2021-03-19","cited_by_count":484},{"id":"1708.05866","title":"A Brief Survey of Deep Reinforcement Learning","created":"2017-08-19","cited_by_count":483},{"id":"2206.06488","title":"Multimodal Learning with Transformers: A Survey","created":"2022-06-13","cited_by_count":400},{"id":"1903.08254","title":"Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables","created":"2019-03-19","cited_by_count":389},{"id":"1906.03731","title":"Is Attention Interpretable?","created":"2019-06-09","cited_by_count":389},{"id":"2302.09419","title":"A Comprehensive Survey on Pretrained Foundation Models: A History from BERT to ChatGPT","created":"2023-02-18","cited_by_count":368},{"id":"1912.12180","title":"Axial Attention in Multidimensional Transformers","created":"2019-12-20","cited_by_count":358},{"id":"1912.08226","title":"Meshed-Memory Transformer for Image Captioning","created":"2019-12-17","cited_by_count":343},{"id":"2209.00588","title":"Transformers are Sample-Efficient World Models","created":"2022-09-01","cited_by_count":328},{"id":"2004.05155","title":"Learning to Explore using Active Neural SLAM","created":"2020-04-10","cited_by_count":316},{"id":"1908.08796","title":"Reinforcement Learning in Healthcare: A Survey","created":"2019-08-22","cited_by_count":310},{"id":"1502.05700","title":"Scalable Bayesian Optimization Using Deep Neural Networks","created":"2015-02-19","cited_by_count":284},{"id":"1708.04782","title":"StarCraft II: A New Challenge for Reinforcement Learning","created":"2017-08-16","cited_by_count":274},{"id":"1910.01741","title":"Improving Sample Efficiency in Model-Free Reinforcement Learning from Images","created":"2019-10-02","cited_by_count":274},{"id":"1910.06764","title":"Stabilizing Transformers for Reinforcement Learning","created":"2019-10-13","cited_by_count":270},{"id":"2003.03600","title":"Reinforcement Learning for Combinatorial Optimization: A Survey","created":"2020-03-07","cited_by_count":236},{"id":"2205.15241","title":"Multi-Game Decision Transformers","created":"2022-05-30","cited_by_count":214},{"id":"2004.08249","title":"Understanding the Difficulty of Training Transformers","created":"2020-04-17","cited_by_count":210},{"id":"1802.08757","title":"Fully Decentralized Multi-Agent Reinforcement Learning with Networked Agents","created":"2018-02-23","cited_by_count":194},{"id":"2109.11251","title":"Trust Region Policy Optimisation in Multi-Agent Reinforcement Learning","created":"2021-09-23","cited_by_count":186},{"id":"2206.14244","title":"Masked World Models for Visual Control","created":"2022-06-28","cited_by_count":170},{"id":"1912.05784","title":"Learning Improvement Heuristics for Solving Routing Problems","created":"2019-12-12","cited_by_count":164},{"id":"2205.14953","title":"Multi-Agent Reinforcement Learning is a Sequence Modeling Problem","created":"2022-05-30","cited_by_count":155},{"id":"1908.03963","title":"A Review of Cooperative Multi-Agent Deep Reinforcement Learning","created":"2019-08-11","cited_by_count":147},{"id":"2206.13499","title":"Prompting Decision Transformer for Few-Shot Policy Generalization","created":"2022-06-27","cited_by_count":146},{"id":"2202.09481","title":"TransDreamer: Reinforcement Learning with Transformer World Models","created":"2022-02-19","cited_by_count":143},{"id":"2010.10042","title":"Improving Factual Completeness and Consistency of Image-to-Text Radiology Report Generation","created":"2020-10-20","cited_by_count":141},{"id":"2209.04881","title":"On The Computational Complexity of Self-Attention","created":"2022-09-11","cited_by_count":139},{"id":"2303.07109","title":"Transformer-based World Models Are Happy With 100k Interactions","created":"2023-03-13","cited_by_count":139},{"id":"1901.05353","title":"A Primer on PAC-Bayesian Learning","created":"2019-01-16","cited_by_count":132},{"id":"2110.11945","title":"SOFT: Softmax-free Transformer with Linear Complexity","created":"2021-10-22","cited_by_count":128},{"id":"1802.04181","title":"State Representation Learning for Control: An Overview","created":"2018-02-12","cited_by_count":127},{"id":"1812.11794","title":"Deep Reinforcement Learning for Multi-Agent Systems: A Review of Challenges, Solutions and Applications","created":"2018-12-31","cited_by_count":127},{"id":"1912.02875","title":"Reinforcement Learning Upside Down: Don't Predict Rewards -- Just Map Them to Actions","created":"2019-12-05","cited_by_count":125},{"id":"2007.04976","title":"One Policy to Control Them All: Shared Modular Policies for Agent-Agnostic Control","created":"2020-07-09","cited_by_count":121},{"id":"2209.03993","title":"Q-learning Decision Transformer: Leveraging Dynamic Programming for Conditional Sequence Modelling in Offline RL","created":"2022-09-08","cited_by_count":103},{"id":"2204.08967","title":"When Is Partially Observable Reinforcement Learning Not Scary?","created":"2022-04-19","cited_by_count":100},{"id":"2008.06693","title":"Explainability in Deep Reinforcement Learning","created":"2020-08-15","cited_by_count":97},{"id":"2006.09286","title":"On the Computational Power of Transformers and its Implications in Sequence Modeling","created":"2020-06-16","cited_by_count":85},{"id":"2103.06104","title":"U-Net Transformer: Self and Cross Attention for Medical Image Segmentation","created":"2021-03-10","cited_by_count":81},{"id":"2303.00957","title":"Preference Transformer: Modeling Human Preferences using Transformers for RL","created":"2023-03-02","cited_by_count":79},{"id":"2011.14826","title":"Revisiting Rainbow: Promoting more Insightful and Inclusive Deep Reinforcement Learning Research","created":"2020-11-20","cited_by_count":78},{"id":"1912.10944","title":"A Survey of Deep Reinforcement Learning in Video Games","created":"2019-12-23","cited_by_count":73},{"id":"2112.13112","title":"A Survey on Interpretable Reinforcement Learning","created":"2021-12-24","cited_by_count":73},{"id":"2010.01856","title":"My Body is a Cage: the Role of Morphology in Graph-Based Incompatible Control","created":"2020-10-05","cited_by_count":70},{"id":"2011.09464","title":"Counterfactual Credit Assignment in Model-Free Reinforcement Learning","created":"2020-11-18","cited_by_count":64},{"id":"2107.05768","title":"Combiner: Full Attention Transformer with Sparse Computation Cost","created":"2021-07-12","cited_by_count":64},{"id":"2205.15967","title":"You Can't Count on Luck: Why Decision Transformers and RvS Fail in Stochastic Environments","created":"2022-05-31","cited_by_count":63},{"id":"2206.04779","title":"Challenges and Opportunities in Offline Reinforcement Learning from Visual Observations","created":"2022-06-09","cited_by_count":63},{"id":"2303.01859","title":"POPGym: Benchmarking Partially Observable Reinforcement Learning","created":"2023-03-03","cited_by_count":62},{"id":"1810.06721","title":"Optimizing Agent Behavior over Long Time Scales by Transporting Value","created":"2018-10-15","cited_by_count":58},{"id":"2202.04500","title":"Contextualize Me -- The Case for Context in Reinforcement Learning","created":"2022-02-09","cited_by_count":46},{"id":"2006.05656","title":"Why Attentions May Not Be Interpretable?","created":"2020-06-10","cited_by_count":41},{"id":"2206.06614","title":"Transformers are Meta-Reinforcement Learners","created":"2022-06-14","cited_by_count":41},{"id":"2101.08001","title":"UPDeT: Universal Multi-agent Reinforcement Learning via Policy Decoupling with Transformers","created":"2021-01-20","cited_by_count":39},{"id":"2110.03864","title":"Boundary-aware Transformers for Skin Lesion Segmentation","created":"2021-10-08","cited_by_count":39},{"id":"2206.08569","title":"Bootstrapped Transformer for Offline Reinforcement Learning","created":"2022-06-17","cited_by_count":37},{"id":"1909.02790","title":"From Few to More: Large-scale Dynamic Multiagent Curriculum Learning","created":"2019-09-06","cited_by_count":36},{"id":"2206.01078","title":"Deep Transformer Q-Networks for Partially Observable Reinforcement Learning","created":"2022-06-02","cited_by_count":36},{"id":"1912.05537","title":"Encoding Musical Style with Transformer Autoencoders","created":"2019-12-10","cited_by_count":35},{"id":"2108.05305","title":"ConvNets vs. Transformers: Whose Visual Representations are More Transferable?","created":"2021-08-11","cited_by_count":35},{"id":"2112.02845","title":"Offline Pre-trained Multi-Agent Decision Transformer: One Big Sequence Model Tackles All SMAC Tasks","created":"2021-12-06","cited_by_count":32},{"id":"2007.05520","title":"Representations for Stable Off-Policy Reinforcement Learning","created":"2020-07-10","cited_by_count":31},{"id":"2202.08434","title":"A Survey of Explainable Reinforcement Learning","created":"2022-02-17","cited_by_count":31}],"next_cursor":"100"}