- Rating
- 3(+1)
- Confidence
- 2(−1)
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 3
Read review
Paper summary
This paper proposes the Decomposed World Model (DWM), which separates the world effect arising from the environment's intrinsic dynamics from the action effect caused by the agent's actions in latent world models. The method uses an auxiliary world head, a world-contrastive objective, and an orthogonality constraint to encourage this decomposition. It is evaluated on PushT-W, Reacher-W, TwoRoom-W, and Ball-in-Cup, and improves prediction and planning performance with both LeWM and DINO-WM backbones.
Critical strengths
-
The motivation is clear: separating dynamics that persist under a null action, such as gravity, inertia, and drift, from the effects of the agent's actions is a reasonable problem formulation.
-
The method is simple and can be readily integrated into existing world models. DWM preserves the original model's inference and CEM planning pipeline, and the auxiliary world head is used only during training. The authors observe improvements with both LeWM and the structurally different DINO-WM.
-
The experimental design is relatively comprehensive. In addition to the main experiments, the paper examines the world head's action invariance, 20-step rollouts, OOD gravity, and flat counterparts without persistent world effects, providing evidence for the method's effectiveness.
Critical weaknesses
-
The current experiments primarily establish that the world head is insensitive to actions. They do not directly demonstrate that its learned representation corresponds to the counterfactual world effect defined in the paper. Evidence for the identifiability of the central decomposition therefore remains insufficient.
-
The three core W-variants are purpose-built environments with artificially introduced persistent world effects. The evaluation also lacks a direct comparison with closely related methods that separate controllable and non-controllable dynamics, such as Iso-Dream.
Questions for authors
-
Could the authors use the simulator to construct counterfactual transitions under a null action from the same state and history, and test whether the learned world component agrees with the corresponding ground-truth zero-action transition?
-
Could the authors include Iso-Dream or other baselines that separate controllable and non-controllable dynamics, and evaluate the method on additional DMControl or robotic tasks that naturally involve gravity, inertia, or contact dynamics? The current evaluation covers only four environments, which is relatively limited compared with typical evaluations of world-model performance.
I would raise my score if the authors satisfactorily address these two questions, particularly by providing the experimental validation requested in Question 1.
10 comments
W2. The three core W-variants are purpose-built environments with artificially introduced persistent world effects. The evaluation also lacks a direct comparison with closely related methods that separate controllable and non-controllable dynamics, such as Iso-Dream.(part 2/2)
Second, to directly compare DWM with related approaches that disentangle controllable and non-controllable dynamics, we implemented an Iso-Dream baseline under the same experimental setting as LeWM. Specifically, following Iso-Dream's controllable/non-controllable dynamics factorization, we use separate action-conditioned and action-free latent transition models, together with inverse-action supervision on the difference between their predictions. This allows us to directly compare the dynamics-factorization principle under the same offline data, training protocol, and latent-space CEM planning framework. We also included SD-JEPA, which decomposes the JEPA latent representation into orthogonal progression and content subspaces. Unlike DWM, which separates the causes of the predicted transition into an action-invariant world component and a complementary action-related residual, SD-JEPA separates what the latent state represents (task progression versus content).
All methods use the same offline trajectories, initialization, training-update budget, latent-space CEM planner, and evaluation protocol. Success rates are averaged over three planner seeds.
| Method | PushT-W | Reacher-W | TwoRoom-W |
|---|---|---|---|
| LeWM | 32.0 | 60.0 | 60.0 |
| Iso-Dream | 28.7 | 58.7 | 63.3 |
| SD-JEPA | 34.7 | 62.0 | 66.0 |
| DWM | 44.0 | 70.7 | 76.7 |
The Iso-Dream factorization does not consistently improve over LeWM, while SD-JEPA provides modest gains. DWM consistently outperforms both decomposition baselines, with improvements over SD-JEPA of 9.3, 8.7, and 10.7 percentage points on PushT-W, Reacher-W, and TwoRoom-W, respectively. These results demonstrate that DWM's improvements are not simply reproduced by existing controllable/non-controllable dynamics factorization or orthogonal latent-subspace decomposition.
Taken together, these additional experiments demonstrate that DWM's benefits extend beyond artificially constructed W-variants and that its improvements cannot be reproduced by generic controllable/non-controllable dynamics factorization alone. They further support the effectiveness of explicitly learning action-independent world effects for planning under external dynamics.
Q1. Could the authors use the simulator to construct counterfactual transitions under a null action from the same state and history, and test whether the learned world component agrees with the corresponding ground-truth zero-action transition?
A3. Thank you for this important suggestion. To further investigate what the world head actually learns and whether it converges to a trivial solution, we designed an additional experiment following your suggestion. Specifically, we examine whether the world-head predictions correspond to the actual environment evolution under null actions.
We randomly sampled 256 three-frame histories that were not used for training on PushT. For each history, we saved the complete simulator state, including the positions, velocities, angles, and angular velocities of the pusher and block. Starting from the corresponding state and history, the world head predicts the latent representation after a five-step null-action block. Independently, we restored the same simulator state and executed five consecutive null actions, allowing the environment dynamics to evolve. We then encoded the resulting simulator observation using the same encoder to obtain its latent representation. Finally, we measured the correspondence between the world-head predictions and the simulator-derived latent representations using centered linear CKA. We further normalize the CKA using a reference CKA between two independently sampled sets of random features.
| Representation | Relative CKA ↑ |
|---|---|
| World head at initialization | 1.31 |
| World head after training | 18.74 |
The relative CKA increases substantially from 1.31 to 18.74 after training, indicating a strong correspondence between the world-head representations and the actual environment states reached after five null-action steps. This result therefore provides further evidence that the world head learns meaningful representations of action-independent environment dynamics.
Q2. Could the authors include Iso-Dream or other baselines that separate controllable and non-controllable dynamics, and evaluate the method on additional DMControl or robotic tasks that naturally involve gravity, inertia, or contact dynamics? The current evaluation covers only four environments, which is relatively limited compared with typical evaluations of world-model performance.(1/2)
A4. We expanded our evaluation in two directions: adding closely related dynamics-decomposition baselines and evaluating DWM on additional environments with native physical dynamics.
(1) Comparison with related decomposition baselines. We added two closely related baselines, Iso-Dream and SD-JEPA, and evaluated them on all three W-tasks.
We implemented an Iso-Dream baseline under the same experimental setting as LeWM. Specifically, following Iso-Dream's controllable/non-controllable dynamics factorization, we use separate action-conditioned and action-free latent transition models, together with inverse-action supervision on the difference between their predictions. This allows us to directly compare the dynamics-factorization principle under the same offline data, training protocol, and latent-space CEM planning framework. We also included SD-JEPA, which decomposes the JEPA latent representation into orthogonal progression and content subspaces. Unlike DWM, which separates the causes of the predicted transition into an action-invariant world component and a complementary action-related residual, SD-JEPA separates what the latent state represents (task progression versus content).
All methods use the same offline trajectories, initialization, training-update budget, latent-space CEM planner, and evaluation protocol. Success rates are averaged over three planner seeds.
| Method | PushT-W | Reacher-W | TwoRoom-W |
|---|---|---|---|
| LeWM | 32.0 | 60.0 | 60.0 |
| Iso-Dream | 28.7 | 58.7 | 63.3 |
| SD-JEPA | 34.7 | 62.0 | 66.0 |
| DWM | 44.0 | 70.7 | 76.7 |
The Iso-Dream factorization does not consistently improve over LeWM, while SD-JEPA provides modest gains. DWM consistently outperforms both decomposition baselines, with improvements over SD-JEPA of 9.3, 8.7, and 10.7 percentage points on PushT-W, Reacher-W, and TwoRoom-W, respectively. These results demonstrate that DWM's improvements are not simply reproduced by existing controllable/non-controllable dynamics factorization or orthogonal latent-subspace decomposition.
We sincerely thank Reviewer nc32 for the careful review and concrete suggestions for strengthening the paper. We address your comments below.
W1. The current experiments primarily establish that the world head is insensitive to actions. They do not directly demonstrate that its learned representation corresponds to the counterfactual world effect defined in the paper. Evidence for the identifiability of the central decomposition therefore remains insufficient.
A1. Thank you for this important suggestion. To further investigate what the world head actually learns and whether it converges to a trivial solution, we designed an additional experiment. Specifically, we examine whether the world-head predictions correspond to the actual environment evolution under null actions.
We randomly sampled 256 three-frame histories that were not used for training on PushT. For each history, we saved the complete simulator state, including the positions, velocities, angles, and angular velocities of the pusher and block. Starting from the corresponding state and history, the world head predicts the latent representation after a five-step null-action block. Independently, we restored the same simulator state and executed five consecutive null actions, allowing the environment dynamics to evolve. We then encoded the resulting simulator observation using the same encoder to obtain its latent representation. Finally, we measured the correspondence between the world-head predictions and the simulator-derived latent representations using centered linear CKA. We further normalize the CKA using a reference CKA between two independently sampled sets of random features.
The relative CKA increases substantially from 1.31 to 18.74 after training, indicating a strong correspondence between the world-head representations and the actual environment states reached after five null-action steps. This result therefore provides further evidence that the world head learns meaningful representations of action-independent environment dynamics.
W2. The three core W-variants are purpose-built environments with artificially introduced persistent world effects. The evaluation also lacks a direct comparison with closely related methods that separate controllable and non-controllable dynamics, such as Iso-Dream.(part 1/2)
A2. Thank you for raising these concerns. We address them by expanding our evaluation to additional environments and including a comparison with an Iso-Dream baseline.
Indeed, the W-variants are intentionally designed as controlled diagnostic environments. Each preserves the objective and basic structure of its corresponding standard task while introducing one persistent, action-independent source of motion. This design allows us to isolate the effects of external world dynamics without simultaneously changing the task objective.
To examine whether DWM's benefits extend beyond these purpose-built environments, we expanded our evaluation from four to seven environments by adding three unmodified native tasks:
Importantly, these are unmodified native environments without artificially introduced external forces or visual distractors. They therefore allow us to evaluate DWM in environments with naturally occurring contact and physical dynamics. For each task, LeWM and DWM use the same offline trajectories, initialization, training-update budget, action normalization, CEM planner, goal observations, and fixed evaluation cases.
DWM consistently outperforms LeWM across all three additional environments, demonstrating that its benefits extend beyond the original 2D navigation, reaching, and pushing tasks to 3D contact-rich manipulation and control under gravity and inertia.