mlsanityData to 7 Oct 2026

MrCoM: A Meta-Regularized World-Model Generalizing Across Multi-Scenarios

arXiv 2511.06252 ↗First posted 9 Nov 2025cs.LG cs.AIcited by 0

On the map: World models → Latent dynamics models and model-based RL

Abstract (arXiv)

Model-based reinforcement learning (MBRL) is a crucial approach to enhance the generalization capabilities and improve the sample efficiency of RL algorithms. However, current MBRL methods focus primarily on building world models for single tasks and rarely address generalization across different scenarios. Building on the insight that dynamics within the same simulation engine share inherent properties, we attempt to construct a unified world model capable of generalizing across different scenarios, named Meta-Regularized Contextual World-Model (MrCoM). This method first decomposes the latent state space into various components based on the dynamic characteristics, thereby enhancing the accuracy of world-model prediction. Further, MrCoM adopts meta-state regularization to extract unified representation of scenario-relevant information, and meta-value regularization to align world-model optimization with policy learning across diverse scenario objectives. We theoretically analyze the generalization error upper bound of MrCoM in multi-scenario settings. We systematically evaluate our algorithm's generalization ability across diverse scenarios, demonstrating significantly better performance than previous state-of-the-art methods.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Latent dynamics models and model-based RL, one of 11 directions in World models. Builds on 11 of its 27 references that are in the map. First posted on arXiv 9 Nov 2025.

Builds on

11 of 27 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024MAMBA: an Effective World Model Approach for Meta-Reinforcement Learning14 Mar
  2. 2023Mastering Diverse Domains through World Models10 Jan

Other references · 9

  1. 2019Dota 2 with Large Scale Deep Reinforcement Learningcited by 1,084
  2. 2018DeepMind Control Suitecited by 935
  3. 2023Aligning Large Multimodal Models with Factually Augmented RLHFcited by 703
  4. 2019Solving Rubik's Cube with a Robot Handcited by 699
  5. 2016RL2: Fast Reinforcement Learning via Slow Reinforcement Learningcited by 490
  6. 2018Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learningcited by 270
  7. 2018ProMP: Proximal Meta-Policy Searchcited by 91
  8. 2020Objective Mismatch in Model-based Reinforcement Learningcited by 87
  9. 2022Value Gradient weighted Model-Based Reinforcement Learningcited by 31

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024PWM: Policy Learning with Multi-Task World Models
  2. 2026Scaling World-Model Reinforcement Learning Through Diffusion Policy Optimization
  3. 2024Towards Unraveling and Improving Generalization in World Models
  4. 2026PriorZero: Bridging Language Priors and World Models for Decision Making
  5. 2025Accelerating Model-Based Reinforcement Learning with State-Space World Models
  6. 2025Robotic World Model: A Neural Network Simulator for Robust Policy Optimization in Robotics
  7. 2024Meta-DT: Offline Meta-RL as Conditional Sequence Modeling with World Model Disentanglement
  8. 2026Q-Learning With World Models