mlsanityData to 7 Oct 2026

Calibration-risk routing for controlled world-model adaptation

arXiv 2610.01001 ↗First posted 1 Oct 2026cs.AIcited by 0

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

Abstract (arXiv)

Model-based reinforcement learning (MBRL) can exploit simulated experience, but a simulator-to-target shift creates a model-selection problem: correcting the simulator and fitting the target directly can each fail under limited target data. We introduce the Model-Corrected World Model (MC-WM), which separates initial target data into disjoint fit, selection, and calibration partitions and deploys the family with lower standardized calibration risk. A learned confidence signal and deterministic validity predicates weight one-step imagined policy updates without rewriting physical rewards. We evaluate 540 unique reported run cells across three controlled Multi-Joint dynamics with Contact (MuJoCo) shifts; one exact-routing cell was repeated after a pre-deployment artifact gate, giving 541 completed executions.

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 14 of its 17 references that are in the map. First posted on arXiv 1 Oct 2026.

Builds on

14 of 17 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025Adapting World Models with Latent-State Dynamics Residuals3 Apr
  2. 2019Dream to Control: Learning Behaviors by Latent Imagination3 Dec
  3. 2019When to Trust Your Model: Model-Based Policy Optimization19 Jun
  4. 2018Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models30 May

Other references · 10

  1. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  2. 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,401
  3. 2017Constrained Policy Optimizationcited by 928
  4. 2017Sim-to-Real Transfer of Robotic Control with Dynamics Randomizationcited by 616
  5. 2021RMA: Rapid Motor Adaptation for Legged Robotscited by 430
  6. 2022Temporal Difference Learning for Model Predictive Controlcited by 375
  7. 2021Randomized Ensembled Double Q-Learning: Learning Fast Without a Modelcited by 278
  8. 2020Off-Dynamics Reinforcement Learning: Training for Transfer with Domain Classifierscited by 93
  9. 2020Inverse Constrained Reinforcement Learningcited by 45
  10. 2023H2O+: An Improved Framework for Hybrid Offline-and-Online RL with Dynamics Gapscited by 15

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. 2026WAM-RL: World-Action Model Reinforcement Learning with Reconstruction Rewards and Online Video SFT
  3. 2026Scaling World-Model Reinforcement Learning Through Diffusion Policy Optimization
  4. 2026Q-Learning With World Models
  5. 2025Policy-Driven World Model Adaptation for Robust Offline Model-based Reinforcement Learning
  6. 2026Prioritized Rollouts for Efficient World Model-based Vision-Language-Action Policy Optimization
  7. 2026WOMBET: World Model-Based Experience Transfer for Robust and Sample-efficient Reinforcement Learning
  8. 2026Inference Time Policy Optimization for Offline RL with Differentiable World Models