{"list":"other","total":54,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1602.01783","title":"Asynchronous Methods for Deep Reinforcement Learning","created":"2016-02-04","cited_by_count":2258},{"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":"1911.08265","title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","created":"2019-11-19","cited_by_count":1353},{"id":"2301.04104","title":"Mastering Diverse Domains through World Models","created":"2023-01-10","cited_by_count":1253},{"id":"1802.01561","title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures","created":"2018-02-05","cited_by_count":883},{"id":"1601.06759","title":"Pixel Recurrent Neural Networks","created":"2016-01-25","cited_by_count":816},{"id":"2108.13264","title":"Deep Reinforcement Learning at the Edge of the Statistical Precipice","created":"2021-08-30","cited_by_count":807},{"id":"1707.06887","title":"A Distributional Perspective on Reinforcement Learning","created":"2017-07-21","cited_by_count":765},{"id":"2310.16828","title":"TD-MPC2: Scalable, Robust World Models for Continuous Control","created":"2023-10-25","cited_by_count":512},{"id":"1703.04309","title":"End-to-End Learning of Geometry and Context for Deep Stereo Regression","created":"2017-03-13","cited_by_count":360},{"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":"2308.00951","title":"From Sparse to Soft Mixtures of Experts","created":"2023-08-02","cited_by_count":248},{"id":"2205.07802","title":"The Primacy Bias in Deep Reinforcement Learning","created":"2022-05-16","cited_by_count":247},{"id":"2205.15241","title":"Multi-Game Decision Transformers","created":"2022-05-30","cited_by_count":214},{"id":"2302.12902","title":"The Dormant Neuron Phenomenon in Deep Reinforcement Learning","created":"2023-02-24","cited_by_count":174},{"id":"2206.11871","title":"Offline RL for Natural Language Generation with Implicit Language Q Learning","created":"2022-06-05","cited_by_count":138},{"id":"2010.14498","title":"Implicit Under-Parameterization Inhibits Data-Efficient Deep Reinforcement Learning","created":"2020-10-27","cited_by_count":134},{"id":"2309.10150","title":"Q-Transformer: Scalable Offline Reinforcement Learning via Autoregressive Q-Functions","created":"2023-09-18","cited_by_count":131},{"id":"2204.09560","title":"Understanding and Preventing Capacity Loss in Reinforcement Learning","created":"2022-04-20","cited_by_count":125},{"id":"1812.06110","title":"Dopamine: A Research Framework for Deep Reinforcement Learning","created":"2018-12-14","cited_by_count":122},{"id":"1810.00123","title":"Generalization and Regularization in DQN","created":"2018-09-29","cited_by_count":118},{"id":"2402.14083","title":"Beyond A*: Better Planning with Transformers via Search Dynamics Bootstrapping","created":"2024-02-21","cited_by_count":90},{"id":"1803.00455","title":"LCR-Net++: Multi-person 2D and 3D Pose Detection in Natural Images","created":"2018-03-01","cited_by_count":88},{"id":"2011.14826","title":"Revisiting Rainbow: Promoting more Insightful and Inclusive Deep Reinforcement Learning Research","created":"2020-11-20","cited_by_count":78},{"id":"2211.15144","title":"Offline Q-Learning on Diverse Multi-Task Data Both Scales And Generalizes","created":"2022-11-28","cited_by_count":73},{"id":"2011.03148","title":"RetinaGAN: An Object-aware Approach to Sim-to-Real Transfer","created":"2020-11-06","cited_by_count":70},{"id":"1806.04613","title":"Improving Regression Performance with Distributional Losses","created":"2018-06-12","cited_by_count":67},{"id":"2112.04716","title":"DR3: Value-Based Deep Reinforcement Learning Requires Explicit Regularization","created":"2021-12-09","cited_by_count":66},{"id":"2006.02243","title":"The Value-Improvement Path: Towards Better Representations for Reinforcement Learning","created":"2020-06-03","cited_by_count":60},{"id":"2102.13089","title":"On The Effect of Auxiliary Tasks on Representation Dynamics","created":"2021-02-25","cited_by_count":57},{"id":"1901.11530","title":"A Geometric Perspective on Optimal Representations for Reinforcement Learning","created":"2019-01-31","cited_by_count":54},{"id":"2104.06159","title":"Muesli: Combining Improvements in Policy Optimization","created":"2021-04-13","cited_by_count":53},{"id":"2402.04494","title":"Amortized Planning with Large-Scale Transformers: A Case Study on Chess","created":"2024-02-07","cited_by_count":49},{"id":"1901.11084","title":"A Comparative Analysis of Expected and Distributional Reinforcement Learning","created":"2019-01-30","cited_by_count":47},{"id":"2301.08915","title":"Improving Deep Regression with Ordinal Entropy","created":"2023-01-21","cited_by_count":45},{"id":"2304.12567","title":"Proto-Value Networks: Scaling Representation Learning with Auxiliary Tasks","created":"2023-04-25","cited_by_count":42},{"id":"2402.05546","title":"Offline Actor-Critic Reinforcement Learning Scales to Large Models","created":"2024-02-08","cited_by_count":30},{"id":"2211.05641","title":"Regression as Classification: Influence of Task Formulation on Neural Network Features","created":"2022-11-10","cited_by_count":29},{"id":"2203.00543","title":"On the Generalization of Representations in Reinforcement Learning","created":"2022-03-01","cited_by_count":28},{"id":"2305.15703","title":"The Benefits of Being Distributional: Small-Loss Bounds for Reinforcement Learning","created":"2023-05-25","cited_by_count":27},{"id":"2308.10603","title":"A step towards understanding why classification helps regression","created":"2023-08-21","cited_by_count":15},{"id":"2305.18388","title":"The Statistical Benefits of Quantile Temporal-Difference Learning for Value Estimation","created":"2023-05-28","cited_by_count":14},{"id":"2310.15940","title":"Combining Behaviors with the Successor Features Keyboard","created":"2023-10-24","cited_by_count":12},{"id":"2306.10171","title":"Bootstrapped Representations in Reinforcement Learning","created":"2023-06-16","cited_by_count":11},{"id":"2402.13425","title":"Investigating the Histogram Loss in Regression","created":"2024-02-20","cited_by_count":11},{"id":"2304.14421","title":"One-Step Distributional Reinforcement Learning","created":"2023-04-27","cited_by_count":6},{"id":"2211.07447","title":"Neural Regression For Scale-Varying Targets","created":"2022-11-14","cited_by_count":2}],"next_cursor":null}