{"total":131,"rows":[{"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,"area":"wm"},{"id":"2206.07568","title":"Contrastive Learning as Goal-Conditioned Reinforcement Learning","created":"2022-06-15","cited_by_count":253,"area":null},{"id":"2205.15241","title":"Multi-Game Decision Transformers","created":"2022-05-30","cited_by_count":214,"area":"offlinerl"},{"id":"2203.01302","title":"Evolving Curricula with Regret-Based Environment Design","created":"2022-03-02","cited_by_count":173,"area":null},{"id":"2201.08299","title":"Goal-Conditioned Reinforcement Learning: Problems and Solutions","created":"2022-01-20","cited_by_count":158,"area":null},{"id":"2308.10901","title":"Structured World Models from Human Videos","created":"2023-08-21","cited_by_count":147,"area":"wm"},{"id":"2206.04114","title":"Deep Hierarchical Planning from Pixels","created":"2022-06-08","cited_by_count":101,"area":"wm"},{"id":"2201.13425","title":"Don't Change the Algorithm, Change the Data: Exploratory Data for Offline Reinforcement Learning","created":"2022-01-31","cited_by_count":96,"area":"offlinerl"},{"id":"2402.15567","title":"Foundation Policies with Hilbert Representations","created":"2024-02-23","cited_by_count":94,"area":"deeprl"},{"id":"2310.08887","title":"METRA: Scalable Unsupervised RL with Metric-Aware Abstraction","created":"2023-10-13","cited_by_count":86,"area":null},{"id":"2310.10021","title":"Bootstrap Your Own Skills: Learning to Solve New Tasks with Large Language Model Guidance","created":"2023-10-16","cited_by_count":86,"area":"synth"},{"id":"2403.02622","title":"World Models for Autonomous Driving: An Initial Survey","created":"2024-03-05","cited_by_count":80,"area":"wm"},{"id":"2406.17098","title":"Learning Temporal Distances: Contrastive Successor Features Can Provide a Metric Structure for Decision-Making","created":"2024-06-24","cited_by_count":56,"area":"deeprl"},{"id":"2504.11054","title":"Zero-Shot Whole-Body Humanoid Control via Behavioral Foundation Models","created":"2025-04-15","cited_by_count":56,"area":"deeprl"},{"id":"2406.00681","title":"Learning Multimodal Behaviors from Scratch with Diffusion Policy Gradient","created":"2024-06-02","cited_by_count":51,"area":"diffusion"},{"id":"2507.00917","title":"A Survey: Learning Embodied Intelligence from Physical Simulators and World Models","created":"2025-07-01","cited_by_count":51,"area":"wm"},{"id":"2207.07560","title":"Skill-based Model-based Reinforcement Learning","created":"2022-07-15","cited_by_count":50,"area":null},{"id":"2605.12090","title":"World Action Models: The Next Frontier in Embodied AI","created":"2026-05-12","cited_by_count":50,"area":"wm"},{"id":"2302.05103","title":"Controllability-Aware Unsupervised Skill Discovery","created":"2023-02-10","cited_by_count":49,"area":null},{"id":"2301.09816","title":"SMART: Self-supervised Multi-task pretrAining with contRol Transformers","created":"2023-01-24","cited_by_count":44,"area":null},{"id":"2512.24497","title":"What Drives Success in Physical Planning with Joint-Embedding Predictive World Models?","created":"2025-12-30","cited_by_count":43,"area":"wm"},{"id":"2505.00779","title":"Uncertainty-aware Latent Safety Filters for Avoiding Out-of-Distribution Failures","created":"2025-05-01","cited_by_count":33,"area":"wm"},{"id":"2206.11403","title":"Curious Exploration via Structured World Models Yields Zero-Shot Object Manipulation","created":"2022-06-22","cited_by_count":31,"area":"wm"},{"id":"2211.13350","title":"Choreographer: Learning and Adapting Skills in Imagination","created":"2022-11-23","cited_by_count":31,"area":null},{"id":"2512.04797","title":"SIMA 2: A Generalist Embodied Agent for Virtual Worlds","created":"2025-12-04","cited_by_count":31,"area":"agents"},{"id":"2412.12098","title":"MaxInfoRL: Boosting exploration in reinforcement learning through information gain maximization","created":"2024-12-16","cited_by_count":30,"area":"deeprl"},{"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":"2404.01220","title":"Entity-Centric Reinforcement Learning for Object Manipulation from Pixels","created":"2024-04-01","cited_by_count":27,"area":"deeprl"},{"id":"2301.02099","title":"Learning Goal-Conditioned Policies Offline with Self-Supervised Reward Shaping","created":"2023-01-05","cited_by_count":25,"area":null},{"id":"2506.15421","title":"Reward Models in Deep Reinforcement Learning: A Survey","created":"2025-06-18","cited_by_count":25,"area":"alignment"},{"id":"2512.24766","title":"Dream2Flow: Bridging Video Generation and Open-World Manipulation with 3D Object Flow","created":"2025-12-31","cited_by_count":25,"area":null},{"id":"2207.06415","title":"The Free Energy Principle for Perception and Action: A Deep Learning Perspective","created":"2022-07-13","cited_by_count":24,"area":null},{"id":"2302.06604","title":"ALAN: Autonomously Exploring Robotic Agents in the Real World","created":"2023-02-13","cited_by_count":24,"area":null},{"id":"2306.11886","title":"SPRINT: Scalable Policy Pre-Training via Language Instruction Relabeling","created":"2023-06-20","cited_by_count":24,"area":null},{"id":"2306.03346","title":"Stabilizing Contrastive RL: Techniques for Robotic Goal Reaching from Offline Data","created":"2023-06-06","cited_by_count":23,"area":null},{"id":"2311.05067","title":"Accelerating Exploration with Unlabeled Prior Data","created":"2023-11-09","cited_by_count":21,"area":null},{"id":"2412.08021","title":"Can a MISL Fly? Analysis and Ingredients for Mutual Information Skill Learning","created":"2024-12-11","cited_by_count":21,"area":"deeprl"},{"id":"2307.10710","title":"Reparameterized Policy Learning for Multimodal Trajectory Optimization","created":"2023-07-20","cited_by_count":20,"area":null},{"id":"2212.12809","title":"Understanding the Complexity Gains of Single-Task RL with a Curriculum","created":"2022-12-24","cited_by_count":17,"area":null},{"id":"2407.08464","title":"TLDR: Unsupervised Goal-Conditioned RL via Temporal Distance-Aware Representations","created":"2024-07-11","cited_by_count":17,"area":"deeprl"},{"id":"2506.05294","title":"A Smooth Sea Never Made a Skilled SAILOR: Robust Imitation via Learning to Search","created":"2025-06-05","cited_by_count":17,"area":"offlinerl"},{"id":"2306.15934","title":"Curious Replay for Model-based Adaptation","created":"2023-06-28","cited_by_count":16,"area":null},{"id":"2310.07220","title":"COPlanner: Plan to Roll Out Conservatively but to Explore Optimistically for Model-Based RL","created":"2023-10-11","cited_by_count":14,"area":null},{"id":"2403.09859","title":"MAMBA: an Effective World Model Approach for Meta-Reinforcement Learning","created":"2024-03-14","cited_by_count":14,"area":"wm"},{"id":"2410.22600","title":"Solving Minimum-Cost Reach Avoid using Reinforcement Learning","created":"2024-10-29","cited_by_count":14,"area":"deeprl"},{"id":"2210.00999","title":"Latent State Marginalization as a Low-cost Approach for Improving Exploration","created":"2022-10-03","cited_by_count":13,"area":null},{"id":"2211.14296","title":"A System for Morphology-Task Generalization via Unified Representation and Behavior Distillation","created":"2022-11-25","cited_by_count":13,"area":null},{"id":"2303.11166","title":"Imitating Graph-Based Planning with Goal-Conditioned Policies","created":"2023-03-20","cited_by_count":13,"area":null},{"id":"2306.09205","title":"Reward-Free Curricula for Training Robust World Models","created":"2023-06-15","cited_by_count":13,"area":"wm"},{"id":"2307.11049","title":"Breadcrumbs to the Goal: Goal-Conditioned Exploration from Human-in-the-Loop Feedback","created":"2023-07-20","cited_by_count":13,"area":"alignment"},{"id":"2405.09111","title":"CarDreamer: Open-Source Learning Platform for World Model based Autonomous Driving","created":"2024-05-15","cited_by_count":13,"area":"wm"},{"id":"2210.12719","title":"Learning General World Models in a Handful of Reward-Free Deployments","created":"2022-10-23","cited_by_count":12,"area":"wm"},{"id":"2405.18917","title":"Causal Action Influence Aware Counterfactual Data Augmentation","created":"2024-05-29","cited_by_count":12,"area":null},{"id":"2408.08441","title":"D5RL: Diverse Datasets for Data-Driven Deep Reinforcement Learning","created":"2024-08-15","cited_by_count":12,"area":"offlinerl"},{"id":"2505.19850","title":"DISCOVER: Automated Curricula for Sparse-Reward Reinforcement Learning","created":"2025-05-26","cited_by_count":12,"area":"deeprl"},{"id":"2310.17330","title":"CQM: Curriculum Reinforcement Learning with a Quantized World Model","created":"2023-10-26","cited_by_count":11,"area":"wm"},{"id":"2408.14785","title":"Unsupervised-to-Online Reinforcement Learning","created":"2024-08-27","cited_by_count":11,"area":"offlinerl"},{"id":"2505.20425","title":"OSVI-WM: One-Shot Visual Imitation for Unseen Tasks using World-Model-Guided Trajectory Generation","created":"2025-05-26","cited_by_count":11,"area":"wm"},{"id":"2402.06187","title":"Premier-TACO is a Few-Shot Policy Learner: Pretraining Multitask Representation via Temporal Action-Driven Contrastive Loss","created":"2024-02-09","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":"2311.03485","title":"CLIP-Motion: Learning Reward Functions for Robotic Actions Using Consecutive Observations","created":"2023-11-06","cited_by_count":9,"area":null},{"id":"2503.01584","title":"SENSEI: Semantic Exploration Guided by Foundation Models to Learn Versatile World Models","created":"2025-03-03","cited_by_count":9,"area":"wm"},{"id":"2506.08902","title":"Intention-Conditioned Flow Occupancy Models","created":"2025-06-10","cited_by_count":9,"area":null},{"id":"2302.03921","title":"Predictable MDP Abstraction for Unsupervised Model-Based RL","created":"2023-02-08","cited_by_count":8,"area":null},{"id":"2406.00324","title":"Do's and Don'ts: Learning Desirable Skills with Instruction Videos","created":"2024-06-01","cited_by_count":8,"area":null},{"id":"2411.03169","title":"Pre-trained Visual Dynamics Representations for Efficient Policy Learning","created":"2024-11-05","cited_by_count":8,"area":"deeprl"},{"id":"2507.05477","title":"Epistemically-guided forward-backward exploration","created":"2025-07-07","cited_by_count":8,"area":"deeprl"},{"id":"2507.12496","title":"FOUNDER: Grounding Foundation Models in World Models for Open-Ended Embodied Decision Making","created":"2025-07-15","cited_by_count":8,"area":"wm"},{"id":"2509.19555","title":"AnySafe: Adapting Latent Safety Filters at Runtime via Safety Constraint Parameterization in the Latent Space","created":"2025-09-23","cited_by_count":7,"area":"wm"},{"id":"2511.20066","title":"SOMBRL: Scalable and Optimistic Model-Based RL","created":"2025-11-25","cited_by_count":7,"area":"deeprl"},{"id":"2401.00006","title":"Building Open-Ended Embodied Agent via Language-Policy Bidirectional Adaptation","created":"2023-12-12","cited_by_count":6,"area":"agents"},{"id":"2402.18866","title":"Dr. Strategy: Model-Based Generalist Agents with Strategic Dreaming","created":"2024-02-29","cited_by_count":6,"area":"deeprl"},{"id":"2411.02446","title":"Learning World Models for Unconstrained Goal Navigation","created":"2024-11-03","cited_by_count":6,"area":"wm"},{"id":"2502.11537","title":"Simulus: Combining Improvements in Sample-Efficient World Model Agents","created":"2025-02-17","cited_by_count":6,"area":"wm"},{"id":"2505.13144","title":"Temporal Distance-aware Transition Augmentation for Offline Model-based Reinforcement Learning","created":"2025-05-19","cited_by_count":6,"area":"offlinerl"},{"id":"2312.01473","title":"Regularity as Intrinsic Reward for Free Play","created":"2023-12-03","cited_by_count":5,"area":null},{"id":"2202.09976","title":"Goal-directed Planning and Goal Understanding by Active Inference: Evaluation Through Simulated and Physical Robot Experiments","created":"2022-02-21","cited_by_count":4,"area":null},{"id":"2211.10515","title":"Curiosity in Hindsight: Intrinsic Exploration in Stochastic Environments","created":"2022-11-18","cited_by_count":4,"area":null},{"id":"2304.05008","title":"Habits and goals in synergy: a variational Bayesian framework for behavior","created":"2023-04-11","cited_by_count":4,"area":null},{"id":"2310.19261","title":"Diversify & Conquer: Outcome-directed Curriculum RL via Out-of-Distribution Disagreement","created":"2023-10-30","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":"2206.11733","title":"Walk the Random Walk: Learning to Discover and Reach Goals Without Supervision","created":"2022-06-23","cited_by_count":3,"area":null},{"id":"2301.10067","title":"Intrinsic Motivation in Model-based Reinforcement Learning: A Brief Review","created":"2023-01-24","cited_by_count":3,"area":"wm"},{"id":"2311.16996","title":"Goal-conditioned Offline Planning from Curious Exploration","created":"2023-11-28","cited_by_count":3,"area":null},{"id":"2312.05822","title":"Toward Open-ended Embodied Tasks Solving","created":"2023-12-10","cited_by_count":3,"area":null},{"id":"2408.09807","title":"Reset-free Reinforcement Learning with World Models","created":"2024-08-19","cited_by_count":3,"area":"wm"},{"id":"2409.12005","title":"Representing Positional Information in Generative World Models for Object Manipulation","created":"2024-09-18","cited_by_count":3,"area":"wm"},{"id":"2410.08751","title":"Zero-Shot Offline Imitation Learning via Optimal Transport","created":"2024-10-11","cited_by_count":3,"area":"offlinerl"},{"id":"2506.00138","title":"Intrinsic Goals for Autonomous Agents: Model-Based Exploration in Virtual Zebrafish Predicts Ethological Behavior and Whole-Brain Dynamics","created":"2025-05-30","cited_by_count":3,"area":"deeprl"},{"id":"2509.22353","title":"Context and Diversity Matter: The Emergence of In-Context Learning in World Models","created":"2025-09-26","cited_by_count":3,"area":"wm"},{"id":"2510.02287","title":"MultiModal Action Conditioned Video Generation","created":"2025-10-02","cited_by_count":3,"area":"wm"},{"id":"2604.17551","title":"SVL: Goal-Conditioned Reinforcement Learning as Survival Learning","created":"2026-04-19","cited_by_count":3,"area":"deeprl"},{"id":"2607.15550","title":"SeerGuard: A Safety Framework for Mobile GUI Agents via World Model Prediction","created":"2026-07-17","cited_by_count":3,"area":"wm"},{"id":"2210.06168","title":"The Role of Exploration for Task Transfer in Reinforcement Learning","created":"2022-10-11","cited_by_count":2,"area":null},{"id":"2302.03288","title":"Object-Centric Scene Representations using Active Inference","created":"2023-02-07","cited_by_count":2,"area":null},{"id":"2408.11816","title":"Efficient Exploration and Discriminative World Model Learning with an Object-Centric Abstraction","created":"2024-08-21","cited_by_count":2,"area":"wm"},{"id":"2411.14991","title":"Free Energy Projective Simulation (FEPS): Active inference with interpretability","created":"2024-11-22","cited_by_count":2,"area":null},{"id":"2505.07815","title":"Imagine, Verify, Execute: Memory-guided Agentic Exploration with Vision-Language Models","created":"2025-05-12","cited_by_count":2,"area":"mllm"},{"id":"2507.05561","title":"Preemptive Solving of Future Problems: Multitask Preplay in Humans and Machines","created":"2025-07-08","cited_by_count":2,"area":null},{"id":"2510.05996","title":"Information-Theoretic Policy Pre-Training with Empowerment","created":"2025-10-07","cited_by_count":2,"area":"deeprl"}],"next_cursor":"100"}