{"list":"other","total":63,"rows":[{"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":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1801.01290","title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","created":"2018-01-04","cited_by_count":4885},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"1509.02971","title":"Continuous control with deep reinforcement learning","created":"2015-09-09","cited_by_count":3407},{"id":"1308.3432","title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","created":"2013-08-15","cited_by_count":2079},{"id":"1506.02438","title":"High-Dimensional Continuous Control Using Generalized Advantage Estimation","created":"2015-06-08","cited_by_count":2026},{"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":"1811.04551","title":"Learning Latent Dynamics for Planning from Pixels","created":"2018-11-12","cited_by_count":1264},{"id":"1511.05952","title":"Prioritized Experience Replay","created":"2015-11-18","cited_by_count":1099},{"id":"1801.00690","title":"DeepMind Control Suite","created":"2018-01-02","cited_by_count":956},{"id":"1802.01561","title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures","created":"2018-02-05","cited_by_count":883},{"id":"2205.06175","title":"A Generalist Agent","created":"2022-05-12","cited_by_count":808},{"id":"1710.02298","title":"Rainbow: Combining Improvements in Deep Reinforcement Learning","created":"2017-10-06","cited_by_count":786},{"id":"1707.06887","title":"A Distributional Perspective on Reinforcement Learning","created":"2017-07-21","cited_by_count":765},{"id":"2004.04136","title":"CURL: Contrastive Unsupervised Representations for Reinforcement Learning","created":"2020-04-08","cited_by_count":760},{"id":"1606.04934","title":"Improving Variational Inference with Inverse Autoregressive Flow","created":"2016-06-15","cited_by_count":640},{"id":"2007.03898","title":"NVAE: A Deep Hierarchical Variational Autoencoder","created":"2020-07-08","cited_by_count":637},{"id":"1602.04621","title":"Deep Exploration via Bootstrapped DQN","created":"2016-02-15","cited_by_count":527},{"id":"1903.00374","title":"Model-Based Reinforcement Learning for Atari","created":"2019-03-01","cited_by_count":502},{"id":"1912.01588","title":"Leveraging Procedural Generation to Benchmark Reinforcement Learning","created":"2019-12-03","cited_by_count":483},{"id":"2206.08853","title":"MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge","created":"2022-06-17","cited_by_count":478},{"id":"2004.14990","title":"Reinforcement Learning with Augmented Data","created":"2020-04-30","cited_by_count":468},{"id":"1611.05397","title":"Reinforcement Learning with Unsupervised Auxiliary Tasks","created":"2016-11-16","cited_by_count":404},{"id":"2107.09645","title":"Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning","created":"2021-07-20","cited_by_count":372},{"id":"1806.06923","title":"Implicit Quantile Networks for Distributional Reinforcement Learning","created":"2018-06-14","cited_by_count":369},{"id":"2102.06171","title":"High-Performance Large-Scale Image Recognition Without Normalization","created":"2021-02-11","cited_by_count":360},{"id":"2207.01780","title":"CodeRL: Mastering Code Generation through Pretrained Models and Deep Reinforcement Learning","created":"2022-07-05","cited_by_count":358},{"id":"2206.11795","title":"Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos","created":"2022-06-23","cited_by_count":345},{"id":"1806.06920","title":"Maximum a Posteriori Policy Optimisation","created":"2018-06-14","cited_by_count":328},{"id":"2007.05929","title":"Data-Efficient Reinforcement Learning with Self-Predictive Representations","created":"2020-07-12","cited_by_count":318},{"id":"1610.00696","title":"Deep Visual Foresight for Planning Robot Motion","created":"2016-10-03","cited_by_count":285},{"id":"1910.01741","title":"Improving Sample Efficiency in Model-Free Reinforcement Learning from Images","created":"2019-10-02","cited_by_count":274},{"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":"2011.10650","title":"Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on Images","created":"2020-11-20","cited_by_count":264},{"id":"2109.06780","title":"Benchmarking the Spectrum of Agent Capabilities","created":"2021-09-14","cited_by_count":200},{"id":"1804.08617","title":"Distributed Distributional Deterministic Policy Gradients","created":"2018-04-23","cited_by_count":199},{"id":"1802.10567","title":"Learning by Playing - Solving Sparse Reward Tasks from Scratch","created":"2018-02-28","cited_by_count":167},{"id":"2006.05990","title":"What Matters In On-Policy Reinforcement Learning? A Large-Scale Empirical Study","created":"2020-06-10","cited_by_count":162},{"id":"1603.00748","title":"Continuous Deep Q-Learning with Model-based Acceleration","created":"2016-03-02","cited_by_count":157},{"id":"2006.00979","title":"Acme: A Research Framework for Distributed Reinforcement Learning","created":"2020-06-01","cited_by_count":146},{"id":"1906.08226","title":"Unsupervised State Representation Learning in Atari","created":"2019-06-19","cited_by_count":144},{"id":"1809.04474","title":"Multi-task Deep Reinforcement Learning with PopArt","created":"2018-09-12","cited_by_count":141},{"id":"1908.03568","title":"Behaviour Suite for Reinforcement Learning","created":"2019-08-09","cited_by_count":132},{"id":"2009.04416","title":"Phasic Policy Gradient","created":"2020-09-09","cited_by_count":123},{"id":"2206.04114","title":"Deep Hierarchical Planning from Pixels","created":"2022-06-08","cited_by_count":101},{"id":"1810.00597","title":"Taming VAEs","created":"2018-10-01","cited_by_count":85},{"id":"1806.04613","title":"Improving Regression Performance with Distributional Losses","created":"2018-06-12","cited_by_count":67},{"id":"2104.06159","title":"Muesli: Combining Improvements in Policy Optimization","created":"2021-04-13","cited_by_count":53},{"id":"2005.07513","title":"A Distributional View on Multi-Objective Policy Optimization","created":"2020-05-15","cited_by_count":52},{"id":"2206.01634","title":"Reinforcement Learning with Neural Radiance Fields","created":"2022-06-03","cited_by_count":43},{"id":"1909.11583","title":"Off-Policy Actor-Critic with Shared Experience Replay","created":"2019-09-25","cited_by_count":39},{"id":"2106.14876","title":"Multi-task curriculum learning in a complex, visual, hard-exploration domain: Minecraft","created":"2021-06-28","cited_by_count":35},{"id":"2110.00641","title":"Batch size-invariance for policy optimization","created":"2021-10-01","cited_by_count":35},{"id":"1904.10079","title":"The MineRL 2019 Competition on Sample Efficient Reinforcement Learning using Human Priors","created":"2019-04-22","cited_by_count":26},{"id":"2111.03941","title":"Time Discretization-Invariant Safe Action Repetition for Policy Gradient Methods","created":"2021-11-06","cited_by_count":23},{"id":"2002.04839","title":"LaProp: Separating Momentum and Adaptivity in Adam","created":"2020-02-12","cited_by_count":20},{"id":"2208.03374","title":"Learning to Generalize with Object-centric Agents in the Open World Survival Game Crafter","created":"2022-08-05","cited_by_count":13},{"id":"1907.03687","title":"General non-linear Bellman equations","created":"2019-07-08","cited_by_count":8},{"id":"1905.12340","title":"Rethinking Full Connectivity in Recurrent Neural Networks","created":"2019-05-29","cited_by_count":6},{"id":"2006.10178","title":"Variational State-Space Models for Localisation and Dense 3D Mapping in 6 DoF","created":"2020-06-17","cited_by_count":6}],"next_cursor":null}