{"list":"other","total":50,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2303.04137","title":"Diffusion Policy: Visuomotor Policy Learning via Action Diffusion","created":"2023-03-07","cited_by_count":2838},{"id":"2110.06169","title":"Offline Reinforcement Learning with Implicit Q-Learning","created":"2021-10-12","cited_by_count":1293},{"id":"2205.09991","title":"Planning with Diffusion for Flexible Behavior Synthesis","created":"2022-05-20","cited_by_count":1061},{"id":"2106.06860","title":"A Minimalist Approach to Offline Reinforcement Learning","created":"2021-06-12","cited_by_count":899},{"id":"2006.15055","title":"Object-Centric Learning with Slot Attention","created":"2020-06-26","cited_by_count":876},{"id":"1809.01999","title":"Recurrent World Models Facilitate Policy Evolution","created":"2018-09-04","cited_by_count":785},{"id":"1910.00177","title":"Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning","created":"2019-10-01","cited_by_count":782},{"id":"2211.15657","title":"Is Conditional Generative Modeling all you need for Decision-Making?","created":"2022-11-28","cited_by_count":516},{"id":"1805.08296","title":"Data-Efficient Hierarchical Reinforcement Learning","created":"2018-05-21","cited_by_count":455},{"id":"2411.04983","title":"DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning","created":"2024-11-07","cited_by_count":386},{"id":"1703.01161","title":"FeUdal Networks for Hierarchical Reinforcement Learning","created":"2017-03-03","cited_by_count":337},{"id":"2304.10573","title":"IDQL: Implicit Q-Learning as an Actor-Critic Method with Diffusion Policies","created":"2023-04-20","cited_by_count":325},{"id":"1604.06057","title":"Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation","created":"2016-04-20","cited_by_count":286},{"id":"1806.01242","title":"Graph networks as learnable physics engines for inference and control","created":"2018-06-04","cited_by_count":244},{"id":"2410.20092","title":"OGBench: Benchmarking Offline Goal-Conditioned RL","created":"2024-10-26","cited_by_count":238},{"id":"2209.14860","title":"Bridging the Gap to Real-World Object-Centric Learning","created":"2022-09-29","cited_by_count":220},{"id":"2402.01032","title":"Repeat After Me: Transformers are Better than State Space Models at Copying","created":"2024-02-01","cited_by_count":216},{"id":"2001.02407","title":"SPACE: Unsupervised Object-Oriented Scene Representation via Spatial Attention and Decomposition","created":"2020-01-08","cited_by_count":190},{"id":"2307.11949","title":"HIQL: Offline Goal-Conditioned RL with Latent States as Actions","created":"2023-07-22","cited_by_count":141},{"id":"2107.00541","title":"Goal-Conditioned Reinforcement Learning with Imagined Subgoals","created":"2021-07-01","cited_by_count":134},{"id":"2304.01203","title":"Optimal Goal-Reaching Reinforcement Learning via Quasimetric Learning","created":"2023-04-03","cited_by_count":121},{"id":"1910.12827","title":"Entity Abstraction in Visual Model-Based Reinforcement Learning","created":"2019-10-28","cited_by_count":110},{"id":"1910.02384","title":"SCALOR: Generative World Models with Scalable Object Representations","created":"2019-10-06","cited_by_count":108},{"id":"2507.07969","title":"Reinforcement Learning with Action Chunking","created":"2025-07-10","cited_by_count":107},{"id":"2306.04829","title":"Object-Centric Learning for Real-World Videos by Predicting Temporal Feature Similarities","created":"2023-06-07","cited_by_count":78},{"id":"2401.02644","title":"Simple Hierarchical Planning with Diffusion","created":"2024-01-05","cited_by_count":73},{"id":"1905.09275","title":"COBRA: Data-Efficient Model-Based RL through Unsupervised Object Discovery and Curiosity-Driven Exploration","created":"2019-05-22","cited_by_count":57},{"id":"2506.04168","title":"Horizon Reduction Makes RL Scalable","created":"2025-06-04","cited_by_count":57},{"id":"1912.11032","title":"Towards Practical Multi-Object Manipulation using Relational Reinforcement Learning","created":"2019-12-23","cited_by_count":55},{"id":"2302.04419","title":"An Investigation into Pre-Training Object-Centric Representations for Reinforcement Learning","created":"2023-02-09","cited_by_count":49},{"id":"2011.14381","title":"Self-supervised Visual Reinforcement Learning with Object-centric Representations","created":"2020-11-29","cited_by_count":44},{"id":"2410.03072","title":"Multi-Robot Motion Planning with Diffusion Models","created":"2024-10-04","cited_by_count":38},{"id":"2503.00535","title":"What Makes a Good Diffusion Planner for Decision Making?","created":"2025-03-01","cited_by_count":38},{"id":"2206.11403","title":"Curious Exploration via Structured World Models Yields Zero-Shot Object Manipulation","created":"2022-06-22","cited_by_count":31},{"id":"2306.08649","title":"OCAtari: Object-Centric Atari 2600 Reinforcement Learning Environments","created":"2023-06-14","cited_by_count":30},{"id":"2404.01220","title":"Entity-Centric Reinforcement Learning for Object Manipulation from Pixels","created":"2024-04-01","cited_by_count":27},{"id":"2410.08822","title":"SOLD: Slot Object-Centric Latent Dynamics Models for Relational Manipulation Learning from Pixels","created":"2024-10-11","cited_by_count":24},{"id":"2203.05960","title":"Policy Architectures for Compositional Generalization in Control","created":"2022-03-10","cited_by_count":23},{"id":"2204.13661","title":"Toward Compositional Generalization in Object-Oriented World Modeling","created":"2022-04-28","cited_by_count":22},{"id":"2201.13388","title":"Compositional Multi-Object Reinforcement Learning with Linear Relation Networks","created":"2022-01-31","cited_by_count":19},{"id":"2205.15821","title":"Unsupervised Image Representation Learning with Deep Latent Particles","created":"2022-05-31","cited_by_count":19},{"id":"2306.05957","title":"DDLP: Unsupervised Object-Centric Video Prediction with Deep Dynamic Latent Particles","created":"2023-06-09","cited_by_count":19},{"id":"2109.04150","title":"Self-supervised Reinforcement Learning with Independently Controllable Subgoals","created":"2021-09-09","cited_by_count":16},{"id":"2306.16021","title":"Structure in Deep Reinforcement Learning: A Survey and Open Problems","created":"2023-06-28","cited_by_count":16},{"id":"2302.01067","title":"A Survey on Compositional Generalization in Applications","created":"2023-02-02","cited_by_count":12},{"id":"2412.18907","title":"EC-Diffuser: Multi-Object Manipulation via Entity-Centric Behavior Generation","created":"2024-12-25","cited_by_count":8}],"next_cursor":null}