{"list":"other","total":57,"rows":[{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"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":"1907.05600","title":"Generative Modeling by Estimating Gradients of the Data Distribution","created":"2019-07-12","cited_by_count":4101},{"id":"1802.05957","title":"Spectral Normalization for Generative Adversarial Networks","created":"2018-02-16","cited_by_count":1636},{"id":"1606.03476","title":"Generative Adversarial Imitation Learning","created":"2016-06-10","cited_by_count":1597},{"id":"2405.12213","title":"Octo: An Open-Source Generalist Robot Policy","created":"2024-05-20","cited_by_count":1484},{"id":"2009.09761","title":"DiffWave: A Versatile Diffusion Model for Audio Synthesis","created":"2020-09-21","cited_by_count":1354},{"id":"2301.04104","title":"Mastering Diverse Domains through World Models","created":"2023-01-10","cited_by_count":1253},{"id":"2205.09991","title":"Planning with Diffusion for Flexible Behavior Synthesis","created":"2022-05-20","cited_by_count":1061},{"id":"1801.00690","title":"DeepMind Control Suite","created":"2018-01-02","cited_by_count":956},{"id":"1805.01954","title":"Behavioral Cloning from Observation","created":"2018-05-04","cited_by_count":492},{"id":"1710.11248","title":"Learning Robust Rewards with Adversarial Inverse Reinforcement Learning","created":"2017-10-30","cited_by_count":490},{"id":"1701.04862","title":"Towards Principled Methods for Training Generative Adversarial Networks","created":"2017-01-17","cited_by_count":464},{"id":"1811.06711","title":"An Algorithmic Perspective on Imitation Learning","created":"2018-11-16","cited_by_count":459},{"id":"2209.11215","title":"Sampling is as easy as learning the score: theory for diffusion models with minimal data assumptions","created":"2022-09-22","cited_by_count":445},{"id":"1905.00360","title":"Information-Theoretic Considerations in Batch Reinforcement Learning","created":"2019-05-01","cited_by_count":287},{"id":"2211.01916","title":"Improved Analysis of Score-based Generative Modeling: User-Friendly Bounds under Minimal Smoothness Assumptions","created":"2022-11-03","cited_by_count":219},{"id":"1809.02925","title":"Discriminator-Actor-Critic: Addressing Sample Inefficiency and Reward Bias in Adversarial Imitation Learning","created":"2018-09-09","cited_by_count":204},{"id":"2106.12142","title":"IQ-Learn: Inverse soft-Q Learning for Imitation","created":"2021-06-23","cited_by_count":193},{"id":"1911.02256","title":"A Divergence Minimization Perspective on Imitation Learning Methods","created":"2019-11-06","cited_by_count":190},{"id":"2206.06227","title":"Convergence for score-based generative modeling with polynomial complexity","created":"2022-06-13","cited_by_count":177},{"id":"1611.03852","title":"A Connection between Generative Adversarial Networks, Inverse Reinforcement Learning, and Energy-Based Models","created":"2016-11-11","cited_by_count":168},{"id":"2303.01861","title":"Diffusion Models are Minimax Optimal Distribution Estimators","created":"2023-03-03","cited_by_count":165},{"id":"1905.12888","title":"Imitation Learning as $f$-Divergence Minimization","created":"2019-05-30","cited_by_count":123},{"id":"2006.04678","title":"Primal Wasserstein Imitation Learning","created":"2020-06-08","cited_by_count":121},{"id":"1406.5979","title":"Reinforcement and Imitation Learning via Interactive No-Regret Learning","created":"2014-06-23","cited_by_count":118},{"id":"2403.10506","title":"HumanoidBench: Simulated Humanoid Benchmark for Whole-Body Locomotion and Manipulation","created":"2024-03-15","cited_by_count":112},{"id":"1703.01030","title":"Deeply AggreVaTeD: Differentiable Imitation Learning for Sequential Prediction","created":"2017-03-03","cited_by_count":93},{"id":"2103.03236","title":"Of Moments and Matching: A Game-Theoretic Framework for Closing the Imitation Gap","created":"2021-03-04","cited_by_count":81},{"id":"1905.10948","title":"Provably Efficient Imitation Learning from Observation Alone","created":"2019-05-27","cited_by_count":78},{"id":"2407.15007","title":"Is Behavior Cloning All You Need? Understanding Horizon in Imitation Learning","created":"2024-07-20","cited_by_count":74},{"id":"2011.04709","title":"f-IRL: Inverse Reinforcement Learning via State Marginal Matching","created":"2020-11-09","cited_by_count":67},{"id":"2102.02981","title":"Finite Sample Analysis of Minimax Offline Reinforcement Learning: Completeness, Fast Rates and First-Order Efficiency","created":"2021-02-05","cited_by_count":56},{"id":"2302.08560","title":"Dual RL: Unification and New Methods for Reinforcement and Imitation Learning","created":"2023-02-16","cited_by_count":48},{"id":"2102.10769","title":"MobILE: Model-Based Imitation Learning From Observation Alone","created":"2021-02-22","cited_by_count":44},{"id":"2004.09395","title":"Energy-Based Imitation Learning","created":"2020-04-20","cited_by_count":40},{"id":"2303.14623","title":"Inverse Reinforcement Learning without Reinforcement Learning","created":"2023-03-26","cited_by_count":36},{"id":"2307.14619","title":"Provable Guarantees for Generative Behavior Cloning: Bridging Low-Level Stability and High-Level Behavior","created":"2023-07-27","cited_by_count":33},{"id":"2402.08848","title":"Hybrid Inverse Reinforcement Learning","created":"2024-02-13","cited_by_count":32},{"id":"2303.00599","title":"LS-IQ: Implicit Reward Regularization for Inverse Reinforcement Learning","created":"2023-03-01","cited_by_count":29},{"id":"2305.15703","title":"The Benefits of Being Distributional: Small-Loss Bounds for Reinforcement Learning","created":"2023-05-25","cited_by_count":27},{"id":"2402.07198","title":"More Benefits of Being Distributional: Second-Order Bounds for Reinforcement Learning","created":"2024-02-11","cited_by_count":23},{"id":"2006.13258","title":"Adversarial Soft Advantage Fitting: Imitation Learning without Policy Optimization","created":"2020-06-23","cited_by_count":22},{"id":"2409.01369","title":"Imitating Language via Scalable Inverse Reinforcement Learning","created":"2024-09-02","cited_by_count":21},{"id":"2010.01207","title":"$f$-GAIL: Learning $f$-Divergence for Generative Adversarial Imitation Learning","created":"2020-10-02","cited_by_count":20},{"id":"2306.01993","title":"Provable benefits of score matching","created":"2023-06-03","cited_by_count":18},{"id":"2305.11290","title":"Massively Scalable Inverse Reinforcement Learning in Google Maps","created":"2023-05-18","cited_by_count":11},{"id":"2408.08994","title":"Model-based RL as a Minimalist Approach to Horizon-Free and Second-Order Bounds","created":"2024-08-16","cited_by_count":11},{"id":"2406.08805","title":"A Dual Approach to Imitation Learning from Observations with Offline Datasets","created":"2024-06-13","cited_by_count":10},{"id":"2406.11905","title":"EvIL: Evolution Strategies for Generalisable Imitation Learning","created":"2024-06-15","cited_by_count":8},{"id":"2409.12799","title":"The Central Role of the Loss Function in Reinforcement Learning","created":"2024-09-19","cited_by_count":8},{"id":"2404.08513","title":"Adversarial Imitation Learning via Boosting","created":"2024-04-12","cited_by_count":5},{"id":"2406.07253","title":"Hybrid Reinforcement Learning from Offline Observation Alone","created":"2024-06-11","cited_by_count":5}],"next_cursor":null}