Right Ranking, Wrong Scale: Reproducing the Robotic World Model's Dynamics Model and Testing the Uncertainty of Its Follow-up
cs.RO, cs.LG
Submitted: 2026-11-02
Updated: 2026-11-02
Terminology
Sources
- Robotic World Model: A Neural Network Simulator for Robust Policy Optimization in Robotics
- Uncertainty-Aware Robotic World Model Makes Offline Model-Based Reinforcement Learning Work on Real Robots
- Selective Dyna-style Planning Under Limited Model Capacity
- Deep Reinforcement Learning at the Edge of the Statistical Precipice
- A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantification
- Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks
- Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models
- Deep Ensembles: A Loss Landscape Perspective
- On Calibration of Modern Neural Networks
- Learning Latent Dynamics for Planning from Pixels
- Mastering Atari with Discrete World Models
- Training independent subnetworks for robust prediction
- Deep Reinforcement Learning that Matters
- When to Trust Your Model: Model-Based Policy Optimization
- MOReL : Model-Based Offline Reinforcement Learning
- Adam: A Method for Stochastic Optimization
- Accurate Uncertainties for Deep Learning Using Calibrated Regression
- Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles
- Learning Accurate Long-term Dynamics for Model-based Reinforcement Learning
- Why M Heads are Better than One: Training a Diverse Ensemble of Deep Networks
Related papers
- Rethinking Actions: Continuity-Aware Priors for World-Model Planning
- MOSAIC: Modular Obstacle and Spatial-Aware Framework for Manipulation In Cluttered Scenes
- SAGAS: Semantic-Aware Graph-Assisted Stitching for Offline Temporal Logic Planning
- DexSeed: Expanding Human Hand-Object Interactions into Robot Demonstrations for Dexterous Policy Learning
- LaST0.5: A Generalist World Action Model with Interaction-Centric Latent Reasoning
- CIALLO: Learning Shared Intent Representations for Cross-Embodiment Manipulation