{"total":52,"rows":[{"id":"2106.02039","title":"Offline Reinforcement Learning as One Big Sequence Modeling Problem","created":"2021-06-03","cited_by_count":644,"area":"wm"},{"id":"2206.04114","title":"Deep Hierarchical Planning from Pixels","created":"2022-06-08","cited_by_count":101,"area":"wm"},{"id":"2310.08887","title":"METRA: Scalable Unsupervised RL with Metric-Aware Abstraction","created":"2023-10-13","cited_by_count":86,"area":null},{"id":"2110.03655","title":"Augmenting Reinforcement Learning with Behavior Primitives for Diverse Manipulation Tasks","created":"2021-10-07","cited_by_count":78,"area":null},{"id":"2208.10291","title":"Efficient Planning in a Compact Latent Action Space","created":"2022-08-22","cited_by_count":57,"area":null},{"id":"2302.05103","title":"Controllability-Aware Unsupervised Skill Discovery","created":"2023-02-10","cited_by_count":49,"area":null},{"id":"2110.02719","title":"The Information Geometry of Unsupervised Reinforcement Learning","created":"2021-10-06","cited_by_count":37,"area":null},{"id":"2106.14305","title":"Unsupervised Skill Discovery with Bottleneck Option Learning","created":"2021-06-27","cited_by_count":28,"area":null},{"id":"2209.08890","title":"An information-theoretic perspective on intrinsic motivation in reinforcement learning: a survey","created":"2022-09-19","cited_by_count":28,"area":null},{"id":"2310.08581","title":"Universal Visual Decomposer: Long-Horizon Manipulation Made Easy","created":"2023-10-12","cited_by_count":25,"area":null},{"id":"2307.10710","title":"Reparameterized Policy Learning for Multimodal Trajectory Optimization","created":"2023-07-20","cited_by_count":20,"area":null},{"id":"2104.05043","title":"Learn Goal-Conditioned Policy with Intrinsic Motivation for Deep Reinforcement Learning","created":"2021-04-11","cited_by_count":17,"area":null},{"id":"2105.14750","title":"Active Hierarchical Exploration with Stable Subgoal Representation Learning","created":"2021-05-31","cited_by_count":17,"area":null},{"id":"2306.14079","title":"Fighting Uncertainty with Gradients: Offline Reinforcement Learning via Diffusion Score Matching","created":"2023-06-24","cited_by_count":17,"area":"offlinerl"},{"id":"2203.04482","title":"Multi-Agent Policy Transfer via Task Relationship Modeling","created":"2022-03-09","cited_by_count":14,"area":null},{"id":"2303.10859","title":"Improved Sample Complexity for Reward-free Reinforcement Learning under Low-rank MDPs","created":"2023-03-20","cited_by_count":14,"area":null},{"id":"2101.05682","title":"AVGCN: Trajectory Prediction using Graph Convolutional Networks Guided by Human Attention","created":"2021-01-14","cited_by_count":12,"area":null},{"id":"2207.10553","title":"MABe22: A Multi-Species Multi-Task Benchmark for Learned Representations of Behavior","created":"2022-07-21","cited_by_count":12,"area":null},{"id":"2310.00311","title":"Efficient Planning with Latent Diffusion","created":"2023-09-30","cited_by_count":12,"area":"diffusion"},{"id":"2201.09765","title":"Generative Planning for Temporally Coordinated Exploration in Reinforcement Learning","created":"2022-01-24","cited_by_count":10,"area":null},{"id":"2209.01947","title":"MO2: Model-Based Offline Options","created":"2022-09-05","cited_by_count":10,"area":null},{"id":"2310.19424","title":"Variational Curriculum Reinforcement Learning for Unsupervised Discovery of Skills","created":"2023-10-30","cited_by_count":9,"area":null},{"id":"2506.00867","title":"Local Manifold Approximation and Projection for Manifold-Aware Diffusion Planning","created":"2025-06-01","cited_by_count":9,"area":"diffusion"},{"id":"2107.13132","title":"Unsupervised Learning of Neurosymbolic Encoders","created":"2021-07-28","cited_by_count":8,"area":null},{"id":"2206.03597","title":"Meta-Learning Parameterized Skills","created":"2022-06-07","cited_by_count":7,"area":null},{"id":"2110.14182","title":"Evidential Softmax for Sparse Multimodal Distributions in Deep Generative Models","created":"2021-10-27","cited_by_count":6,"area":null},{"id":"2110.09507","title":"Provable Hierarchy-Based Meta-Reinforcement Learning","created":"2021-10-18","cited_by_count":5,"area":null},{"id":"2507.09513","title":"Animal behavioral analysis and neural encoding with transformer-based self-supervised pretraining","created":"2025-07-13","cited_by_count":5,"area":null},{"id":"2206.07041","title":"Learning Behavior Representations Through Multi-Timescale Bootstrapping","created":"2022-06-14","cited_by_count":4,"area":null},{"id":"2303.08811","title":"Relax, it doesn't matter how you get there: A new self-supervised approach for multi-timescale behavior analysis","created":"2023-03-15","cited_by_count":4,"area":null},{"id":"2409.09513","title":"Planning Transformer: Long-Horizon Offline Reinforcement Learning with Planning Tokens","created":"2024-09-14","cited_by_count":4,"area":"offlinerl"},{"id":"2411.04987","title":"Few-Shot Task Learning through Inverse Generative Modeling","created":"2024-11-07","cited_by_count":4,"area":null},{"id":"2210.14685","title":"Leveraging Demonstrations with Latent Space Priors","created":"2022-10-26","cited_by_count":3,"area":null},{"id":"2506.11163","title":"Vector Representations of Vessel Trees","created":"2025-06-11","cited_by_count":3,"area":null},{"id":"2111.07908","title":"Learning to Execute: Efficient Learning of Universal Plan-Conditioned Policies in Robotics","created":"2021-11-15","cited_by_count":2,"area":null},{"id":"2202.08444","title":"A Survey on Deep Reinforcement Learning-based Approaches for Adaptation and Generalization","created":"2022-02-17","cited_by_count":1,"area":null},{"id":"2212.07397","title":"Hierarchical Strategies for Cooperative Multi-Agent Reinforcement Learning","created":"2022-12-14","cited_by_count":1,"area":null},{"id":"2306.08810","title":"Deep Generative Models for Decision-Making and Control","created":"2023-06-15","cited_by_count":1,"area":null},{"id":"2310.01569","title":"Iterative Option Discovery for Planning, by Planning","created":"2023-10-02","cited_by_count":1,"area":null},{"id":"2510.24095","title":"Learning Parameterized Skills from Demonstrations","created":"2025-10-28","cited_by_count":1,"area":null},{"id":"2605.08450","title":"Zero-shot Imitation Learning by Latent Topology Mapping","created":"2026-05-08","cited_by_count":1,"area":"offlinerl"},{"id":"2106.02943","title":"Learning Routines for Effective Off-Policy Reinforcement Learning","created":"2021-06-05","cited_by_count":0,"area":null},{"id":"2107.08183","title":"Hierarchical Reinforcement Learning with Optimal Level Synchronization Based on Flow-Based Deep Generative Model","created":"2021-07-17","cited_by_count":0,"area":null},{"id":"2302.11023","title":"Learning signatures of decision making from many individuals playing the same game","created":"2023-02-21","cited_by_count":0,"area":null},{"id":"2407.07328","title":"CATP: Context-Aware Trajectory Prediction with Competition Symbiosis","created":"2024-07-10","cited_by_count":0,"area":null},{"id":"2503.13194","title":"A representational framework for learning and encoding structurally enriched trajectories in complex agent environments","created":"2025-03-17","cited_by_count":0,"area":null},{"id":"2507.16473","title":"Learning Temporal Abstractions via Variational Homomorphisms in Option-Induced Abstract MDPs","created":"2025-07-22","cited_by_count":0,"area":"lr"},{"id":"2509.21928","title":"SAGE: Scene Graph-Aware Guidance and Execution for Long-Horizon Manipulation Tasks","created":"2025-09-26","cited_by_count":0,"area":null},{"id":"2511.12848","title":"Structured Imitation Learning of Interactive Policies through Inverse Games","created":"2025-11-17","cited_by_count":0,"area":"offlinerl"},{"id":"2606.12200","title":"Implicit Neural Representations of Individual Behavior","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2609.18004","title":"Missing Bridges: Composition-Aware Active Imitation Learning","created":"2026-09-16","cited_by_count":0,"area":"offlinerl"},{"id":"2609.35333","title":"Scalable In-Context Reinforcement Learning with Recurrent Algorithm Distillation","created":"2026-09-28","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}