{"list":"other","total":53,"rows":[{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"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":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"1606.01540","title":"OpenAI Gym","created":"2016-06-05","cited_by_count":1736},{"id":"1912.01603","title":"Dream to Control: Learning Behaviors by Latent Imagination","created":"2019-12-03","cited_by_count":1653},{"id":"1803.10122","title":"World Models","created":"2018-03-27","cited_by_count":1513},{"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":"2301.04104","title":"Mastering Diverse Domains through World Models","created":"2023-01-10","cited_by_count":1253},{"id":"1705.05363","title":"Curiosity-driven Exploration by Self-supervised Prediction","created":"2017-05-15","cited_by_count":1194},{"id":"1705.08690","title":"Continual Learning with Deep Generative Replay","created":"2017-05-24","cited_by_count":1158},{"id":"1511.05952","title":"Prioritized Experience Replay","created":"2015-11-18","cited_by_count":1099},{"id":"2205.09991","title":"Planning with Diffusion for Flexible Behavior Synthesis","created":"2022-05-20","cited_by_count":1061},{"id":"1810.12894","title":"Exploration by Random Network Distillation","created":"2018-10-30","cited_by_count":993},{"id":"1805.12114","title":"Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models","created":"2018-05-30","cited_by_count":774},{"id":"1906.08253","title":"When to Trust Your Model: Model-Based Policy Optimization","created":"2019-06-19","cited_by_count":773},{"id":"1606.01868","title":"Unifying Count-Based Exploration and Intrinsic Motivation","created":"2016-06-06","cited_by_count":639},{"id":"2004.13649","title":"Image Augmentation Is All You Need: Regularizing Deep Reinforcement Learning from Pixels","created":"2020-04-28","cited_by_count":585},{"id":"1602.04621","title":"Deep Exploration via Bootstrapped DQN","created":"2016-02-15","cited_by_count":527},{"id":"2211.15657","title":"Is Conditional Generative Modeling all you need for Decision-Making?","created":"2022-11-28","cited_by_count":516},{"id":"2006.12983","title":"dm_control: Software and Tasks for Continuous Control","created":"2020-06-22","cited_by_count":375},{"id":"2208.04202","title":"Analog Bits: Generating Discrete Data using Diffusion Models with Self-Conditioning","created":"2022-08-08","cited_by_count":373},{"id":"2107.09645","title":"Mastering Visual Continuous Control: Improved Data-Augmented Reinforcement Learning","created":"2021-07-20","cited_by_count":372},{"id":"2101.05982","title":"Randomized Ensembled Double Q-Learning: Learning Fast Without a Model","created":"2021-01-15","cited_by_count":288},{"id":"1706.10295","title":"Noisy Networks for Exploration","created":"2017-06-30","cited_by_count":266},{"id":"2205.07802","title":"The Primacy Bias in Deep Reinforcement Learning","created":"2022-05-16","cited_by_count":247},{"id":"2111.00210","title":"Mastering Atari Games with Limited Data","created":"2021-10-30","cited_by_count":237},{"id":"1812.00568","title":"Visual Foresight: Model-Based Deep Reinforcement Learning for Vision-Based Robotic Control","created":"2018-12-03","cited_by_count":230},{"id":"1804.06893","title":"A Study on Overfitting in Deep Reinforcement Learning","created":"2018-04-18","cited_by_count":174},{"id":"2302.12902","title":"The Dormant Neuron Phenomenon in Deep Reinforcement Learning","created":"2023-02-24","cited_by_count":174},{"id":"1603.00748","title":"Continuous Deep Q-Learning with Model-based Acceleration","created":"2016-03-02","cited_by_count":157},{"id":"1803.00101","title":"Model-Based Value Estimation for Efficient Model-Free Reinforcement Learning","created":"2018-02-28","cited_by_count":156},{"id":"1707.03497","title":"Value Prediction Network","created":"2017-07-11","cited_by_count":117},{"id":"2305.18459","title":"Diffusion Model is an Effective Planner and Data Synthesizer for Multi-Task Reinforcement Learning","created":"2023-05-29","cited_by_count":115},{"id":"1810.02274","title":"Episodic Curiosity through Reachability","created":"2018-10-04","cited_by_count":109},{"id":"1810.12162","title":"Model-Based Active Exploration","created":"2018-10-29","cited_by_count":105},{"id":"2106.04799","title":"Pretraining Representations for Data-Efficient Reinforcement Learning","created":"2021-06-09","cited_by_count":105},{"id":"2303.06614","title":"Synthetic Experience Replay","created":"2023-03-12","cited_by_count":101},{"id":"2311.01223","title":"Diffusion Models for Reinforcement Learning: A Survey","created":"2023-11-02","cited_by_count":91},{"id":"2209.12892","title":"Learning to Learn with Generative Models of Neural Network Checkpoints","created":"2022-09-26","cited_by_count":86},{"id":"2206.04779","title":"Challenges and Opportunities in Offline Reinforcement Learning from Visual Observations","created":"2022-06-09","cited_by_count":63},{"id":"2310.19668","title":"DrM: Mastering Visual Reinforcement Learning through Dormant Ratio Minimization","created":"2023-10-30","cited_by_count":47},{"id":"2010.14496","title":"Generative Temporal Difference Learning for Infinite-Horizon Prediction","created":"2020-10-27","cited_by_count":45},{"id":"1807.05827","title":"Remember and Forget for Experience Replay","created":"2018-07-16","cited_by_count":43},{"id":"2304.10466","title":"Efficient Deep Reinforcement Learning Requires Regulating Overfitting","created":"2023-04-20","cited_by_count":36},{"id":"2312.08533","title":"World Models via Policy-Guided Trajectory Diffusion","created":"2023-12-13","cited_by_count":34},{"id":"2402.03570","title":"Diffusion World Model: Future Modeling Beyond Step-by-Step Rollout for Offline Reinforcement Learning","created":"2024-02-05","cited_by_count":31},{"id":"2208.10483","title":"Prioritizing Samples in Reinforcement Learning with Reducible Loss","created":"2022-08-22","cited_by_count":22},{"id":"1905.04819","title":"Task-Agnostic Dynamics Priors for Deep Reinforcement Learning","created":"2019-05-13","cited_by_count":7},{"id":"1902.08349","title":"Generative Memory for Lifelong Reinforcement Learning","created":"2019-02-22","cited_by_count":2}],"next_cursor":null}