{"total":237,"rows":[{"id":"2301.04104","title":"Mastering Diverse Domains through World Models","created":"2023-01-10","cited_by_count":1253,"area":"wm"},{"id":"2309.17080","title":"GAIA-1: A Generative World Model for Autonomous Driving","created":"2023-09-29","cited_by_count":637,"area":"wm"},{"id":"2310.04406","title":"Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models","created":"2023-10-06","cited_by_count":574,"area":"lr"},{"id":"2310.16828","title":"TD-MPC2: Scalable, Robust World Models for Continuous Control","created":"2023-10-25","cited_by_count":512,"area":"wm"},{"id":"2203.04955","title":"Temporal Difference Learning for Model Predictive Control","created":"2022-03-09","cited_by_count":397,"area":"wm"},{"id":"2209.00588","title":"Transformers are Sample-Efficient World Models","created":"2022-09-01","cited_by_count":328,"area":"wm"},{"id":"2405.12399","title":"Diffusion for World Modeling: Visual Details Matter in Atari","created":"2024-05-20","cited_by_count":300,"area":"wm"},{"id":"2210.10749","title":"Transformers Learn Shortcuts to Automata","created":"2022-10-19","cited_by_count":268,"area":null},{"id":"2304.12210","title":"A Cookbook of Self-Supervised Learning","created":"2023-04-24","cited_by_count":250,"area":null},{"id":"2211.04325","title":"Will we run out of data? Limits of LLM scaling based on human-generated data","created":"2022-10-26","cited_by_count":195,"area":null},{"id":"2412.18319","title":"Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree Search","created":"2024-12-24","cited_by_count":175,"area":"lr"},{"id":"2206.14244","title":"Masked World Models for Visual Control","created":"2022-06-28","cited_by_count":170,"area":"wm"},{"id":"2305.19452","title":"Bigger, Better, Faster: Human-level Atari with human-level efficiency","created":"2023-05-30","cited_by_count":147,"area":null},{"id":"2303.07109","title":"Transformer-based World Models Are Happy With 100k Interactions","created":"2023-03-13","cited_by_count":139,"area":"wm"},{"id":"2302.10329","title":"Harms from Increasingly Agentic Algorithmic Systems","created":"2023-02-20","cited_by_count":135,"area":"agents"},{"id":"2403.08321","title":"ManiGaussian: Dynamic Gaussian Splatting for Multi-task Robotic Manipulation","created":"2024-03-13","cited_by_count":108,"area":null},{"id":"2310.09615","title":"STORM: Efficient Stochastic Transformer based World Models for Reinforcement Learning","created":"2023-10-14","cited_by_count":89,"area":"wm"},{"id":"2403.02622","title":"World Models for Autonomous Driving: An Initial Survey","created":"2024-03-05","cited_by_count":80,"area":"wm"},{"id":"2205.01663","title":"Adversarial Training for High-Stakes Reliability","created":"2022-05-03","cited_by_count":60,"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":"2306.13229","title":"TACO: Temporal Latent Action-Driven Contrastive Loss for Visual Reinforcement Learning","created":"2023-06-22","cited_by_count":57,"area":null},{"id":"2401.08898","title":"Bridging State and History Representations: Understanding Self-Predictive RL","created":"2024-01-17","cited_by_count":54,"area":"deeprl"},{"id":"2411.18478","title":"Beyond Examples: High-level Automated Reasoning Paradigm in In-Context Learning via MCTS","created":"2024-11-27","cited_by_count":54,"area":"lr"},{"id":"2207.08229","title":"Guaranteed Discovery of Control-Endogenous Latent States with Multi-Step Inverse Models","created":"2022-07-17","cited_by_count":45,"area":null},{"id":"2210.07241","title":"Visual Reinforcement Learning with Self-Supervised 3D Representations","created":"2022-10-13","cited_by_count":45,"area":null},{"id":"2305.18499","title":"Pre-training Contextualized World Models with In-the-wild Videos for Reinforcement Learning","created":"2023-05-29","cited_by_count":45,"area":"wm"},{"id":"2306.10711","title":"PLASTIC: Improving Input and Label Plasticity for Sample Efficient Reinforcement Learning","created":"2023-06-19","cited_by_count":42,"area":null},{"id":"2501.16142","title":"Towards General-Purpose Model-Free Reinforcement Learning","created":"2025-01-27","cited_by_count":41,"area":"deeprl"},{"id":"2403.00564","title":"EfficientZero V2: Mastering Discrete and Continuous Control with Limited Data","created":"2024-03-01","cited_by_count":40,"area":"wm"},{"id":"2201.12096","title":"Mask-based Latent Reconstruction for Reinforcement Learning","created":"2022-01-28","cited_by_count":39,"area":null},{"id":"2508.17600","title":"GWM: Towards Scalable Gaussian World Models for Robotic Manipulation","created":"2025-08-25","cited_by_count":39,"area":"wm"},{"id":"2403.04253","title":"Mastering Memory Tasks with World Models","created":"2024-03-07","cited_by_count":38,"area":"wm"},{"id":"2212.14164","title":"On Transforming Reinforcement Learning by Transformer: The Development Trajectory","created":"2022-12-29","cited_by_count":36,"area":null},{"id":"2312.08533","title":"World Models via Policy-Guided Trajectory Diffusion","created":"2023-12-13","cited_by_count":34,"area":"wm"},{"id":"2406.19320","title":"Efficient World Models with Context-Aware Tokenization","created":"2024-06-27","cited_by_count":33,"area":"wm"},{"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,"area":"wm"},{"id":"2511.05963","title":"Next-Latent Prediction Transformers Learn Compact World Models","created":"2025-11-08","cited_by_count":31,"area":"wm"},{"id":"2209.07550","title":"Human-level Atari 200x faster","created":"2022-09-15","cited_by_count":28,"area":null},{"id":"2309.14236","title":"MoDem-V2: Visuo-Motor World Models for Real-World Robot Manipulation","created":"2023-09-25","cited_by_count":28,"area":"wm"},{"id":"2505.15692","title":"TemplateRL: Structured Template-Guided Reinforcement Learning for LLM Reasoning","created":"2025-05-21","cited_by_count":28,"area":"lr"},{"id":"2405.18418","title":"Hierarchical World Models as Visual Whole-Body Humanoid Controllers","created":"2024-05-28","cited_by_count":27,"area":"wm"},{"id":"2203.08398","title":"COPA: Certifying Robust Policies for Offline Reinforcement Learning against Poisoning Attacks","created":"2022-03-16","cited_by_count":26,"area":"offlinerl"},{"id":"2310.03022","title":"Decision ConvFormer: Local Filtering in MetaFormer is Sufficient for Decision Making","created":"2023-10-04","cited_by_count":26,"area":"offlinerl"},{"id":"2502.09886","title":"Video2Policy: Scaling up Manipulation Tasks in Simulation through Internet Videos","created":"2025-02-14","cited_by_count":26,"area":"vla"},{"id":"2405.15369","title":"Cross-Domain Policy Adaptation by Capturing Representation Mismatch","created":"2024-05-24","cited_by_count":25,"area":"deeprl"},{"id":"2307.03567","title":"SpawnNet: Learning Generalizable Visuomotor Skills from Pre-trained Networks","created":"2023-07-07","cited_by_count":24,"area":null},{"id":"2403.19925","title":"Decision Mamba: Reinforcement Learning via Sequence Modeling with Selective State Spaces","created":"2024-03-29","cited_by_count":24,"area":"ssm"},{"id":"2310.00344","title":"HarmonyDream: Task Harmonization Inside World Models","created":"2023-09-30","cited_by_count":22,"area":"wm"},{"id":"2509.06863","title":"floq: Training Critics via Flow-Matching for Scaling Compute in Value-Based RL","created":"2025-09-08","cited_by_count":22,"area":"diffusion"},{"id":"2210.09598","title":"Planning for Sample Efficient Imitation Learning","created":"2022-10-18","cited_by_count":20,"area":"offlinerl"},{"id":"2307.10710","title":"Reparameterized Policy Learning for Multimodal Trajectory Optimization","created":"2023-07-20","cited_by_count":20,"area":null},{"id":"2310.08348","title":"LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios","created":"2023-10-12","cited_by_count":20,"area":null},{"id":"2503.04416","title":"Learning Transformer-based World Models with Contrastive Predictive Coding","created":"2025-03-06","cited_by_count":20,"area":"wm"},{"id":"2306.13840","title":"Beyond Scale: The Diversity Coefficient as a Data Quality Metric for Variability in Natural Language Data","created":"2023-06-24","cited_by_count":19,"area":null},{"id":"2310.02635","title":"Reinforcement Learning with Foundation Priors: Let the Embodied Agent Efficiently Learn on Its Own","created":"2023-10-04","cited_by_count":19,"area":"agents"},{"id":"2507.08800","title":"NeuralOS: Towards Simulating Operating Systems via Neural Generative Models","created":"2025-07-11","cited_by_count":19,"area":null},{"id":"2204.10817","title":"Reward Reports for Reinforcement Learning","created":"2022-04-22","cited_by_count":18,"area":null},{"id":"2211.02222","title":"The Benefits of Model-Based Generalization in Reinforcement Learning","created":"2022-11-04","cited_by_count":17,"area":null},{"id":"2306.09466","title":"Simplified Temporal Consistency Reinforcement Learning","created":"2023-06-15","cited_by_count":17,"area":null},{"id":"2503.18871","title":"Bootstrapped Model Predictive Control","created":"2025-03-24","cited_by_count":16,"area":null},{"id":"2206.12542","title":"Value-Consistent Representation Learning for Data-Efficient Reinforcement Learning","created":"2022-06-25","cited_by_count":15,"area":null},{"id":"2208.12345","title":"Light-weight probing of unsupervised representations for Reinforcement Learning","created":"2022-08-25","cited_by_count":15,"area":null},{"id":"2210.10763","title":"On the Feasibility of Cross-Task Transfer with Model-Based Reinforcement Learning","created":"2022-10-19","cited_by_count":15,"area":null},{"id":"2301.12962","title":"Hierarchical Imitation Learning with Vector Quantized Models","created":"2023-01-30","cited_by_count":15,"area":"offlinerl"},{"id":"2511.02097","title":"A Step Toward World Models: A Survey on Robotic Manipulation","created":"2025-10-31","cited_by_count":15,"area":"wm"},{"id":"2306.00867","title":"IQL-TD-MPC: Implicit Q-Learning for Hierarchical Model Predictive Control","created":"2023-06-01","cited_by_count":14,"area":"offlinerl"},{"id":"2310.11305","title":"MiniZero: Comparative Analysis of AlphaZero and MuZero on Go, Othello, and Atari Games","created":"2023-10-17","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":"2203.08222","title":"Zipfian environments for Reinforcement Learning","created":"2022-03-15","cited_by_count":13,"area":null},{"id":"2307.14993","title":"Thinker: Learning to Plan and Act","created":"2023-07-27","cited_by_count":13,"area":"wm"},{"id":"2403.12309","title":"Reinforcement Learning from Delayed Observations via World Models","created":"2024-03-18","cited_by_count":13,"area":"wm"},{"id":"2405.15083","title":"MuDreamer: Learning Predictive World Models without Reconstruction","created":"2024-05-23","cited_by_count":13,"area":"wm"},{"id":"2410.18082","title":"Prioritized Generative Replay","created":"2024-10-23","cited_by_count":13,"area":"deeprl"},{"id":"2502.01591","title":"Improving Transformer World Models for Data-Efficient RL","created":"2025-02-03","cited_by_count":13,"area":"wm"},{"id":"2502.19009","title":"Distilling Reinforcement Learning Algorithms for In-Context Model-Based Planning","created":"2025-02-26","cited_by_count":13,"area":"deeprl"},{"id":"2206.04384","title":"Value Memory Graph: A Graph-Structured World Model for Offline Reinforcement Learning","created":"2022-06-09","cited_by_count":12,"area":"wm"},{"id":"2305.18443","title":"Off-Policy RL Algorithms Can be Sample-Efficient for Continuous Control via Sample Multiple Reuse","created":"2023-05-29","cited_by_count":12,"area":null},{"id":"2312.15908","title":"Decentralized Monte Carlo Tree Search for Partially Observable Multi-agent Pathfinding","created":"2023-12-26","cited_by_count":12,"area":null},{"id":"2406.10667","title":"UniZero: Generalized and Efficient Planning with Scalable Latent World Models","created":"2024-06-15","cited_by_count":12,"area":"wm"},{"id":"2506.10137","title":"Self-Predictive Representations for Combinatorial Generalization in Behavioral Cloning","created":"2025-06-11","cited_by_count":12,"area":"offlinerl"},{"id":"2510.13704","title":"Simplicial Embeddings Improve Sample Efficiency in Actor-Critic Agents","created":"2025-10-15","cited_by_count":12,"area":"deeprl"},{"id":"2402.05643","title":"Improving Token-Based World Models with Parallel Observation Prediction","created":"2024-02-08","cited_by_count":11,"area":"wm"},{"id":"2410.11234","title":"Bayes Adaptive Monte Carlo Tree Search for Offline Model-based Reinforcement Learning","created":"2024-10-15","cited_by_count":11,"area":"offlinerl"},{"id":"2501.13075","title":"Evolution and The Knightian Blindspot of Machine Learning","created":"2025-01-22","cited_by_count":11,"area":null},{"id":"2502.19805","title":"Implicit Search via Discrete Diffusion: A Study on Chess","created":"2025-02-27","cited_by_count":11,"area":"diffusion"},{"id":"2509.25454","title":"DeepSearch: Overcome the Bottleneck of Reinforcement Learning with Verifiable Rewards via Monte Carlo Tree Search","created":"2025-09-29","cited_by_count":11,"area":"lr"},{"id":"2203.16707","title":"Monte Carlo Tree Search based Hybrid Optimization of Variational Quantum Circuits","created":"2022-03-30","cited_by_count":10,"area":null},{"id":"2208.01545","title":"The Curse of Low Task Diversity: On the Failure of Transfer Learning to Outperform MAML and Their Empirical Equivalence","created":"2022-08-02","cited_by_count":10,"area":null},{"id":"2306.09526","title":"Residual Q-Learning: Offline and Online Policy Customization without Value","created":"2023-06-15","cited_by_count":10,"area":"offlinerl"},{"id":"2501.16443","title":"Object-Centric World Models from Few-Shot Annotations for Sample-Efficient Reinforcement Learning","created":"2025-01-27","cited_by_count":10,"area":"wm"},{"id":"2502.07591","title":"DMWM: Dual-Mind World Model with Long-Term Imagination","created":"2025-02-11","cited_by_count":10,"area":"wm"},{"id":"2603.18202","title":"R2-Dreamer: Redundancy-Reduced World Models without Decoders or Augmentation","created":"2026-03-18","cited_by_count":10,"area":"wm"},{"id":"2307.13453","title":"Monte-Carlo Tree Search for Multi-Agent Pathfinding: Preliminary Results","created":"2023-07-25","cited_by_count":9,"area":null},{"id":"2402.17975","title":"Sample-Efficient Preference-based Reinforcement Learning with Dynamics Aware Rewards","created":"2024-02-28","cited_by_count":9,"area":"alignment"},{"id":"2405.11778","title":"Efficient Multi-agent Reinforcement Learning by Planning","created":"2024-05-20","cited_by_count":9,"area":null},{"id":"2406.02696","title":"iQRL -- Implicitly Quantized Representations for Sample-efficient Reinforcement Learning","created":"2024-06-04","cited_by_count":9,"area":"deeprl"},{"id":"2505.20922","title":"Revisiting Multi-Agent World Modeling from a Diffusion-Inspired Perspective","created":"2025-05-27","cited_by_count":9,"area":"wm"},{"id":"2506.08460","title":"MOBODY: Model Based Off-Dynamics Offline Reinforcement Learning","created":"2025-06-10","cited_by_count":9,"area":"offlinerl"},{"id":"2310.05167","title":"Hieros: Hierarchical Imagination on Structured State Space Sequence World Models","created":"2023-10-08","cited_by_count":8,"area":"wm"},{"id":"2405.16030","title":"Constrained Ensemble Exploration for Unsupervised Skill Discovery","created":"2024-05-25","cited_by_count":8,"area":"deeprl"}],"next_cursor":"100"}