- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
ReL-WM adds a relational state to DreamerV3. Scene graphs describe object positions, physical interactions, and changes in task progress. The model learns to predict this information during imagined rollouts. Milestones extracted from demonstrations provide an additional reward-shaping signal. Experiments cover tabletop manipulation, mobile manipulation, object transfer, and changes in scene layout and lighting.
Critical strengths
-
Modeling interaction states such as contact, grasp, and support is a useful direction for manipulation world models. These states can distinguish situations that look similar in images but require different actions.
-
The experiments show consistent improvements across several settings. The ablations also separate progress prediction from reward shaping: on PlaceSphere, the method reaches 78.2% success without shaping and 86.7% with the default shaping weight. This helps show that the gains are not entirely due to the added reward.
Critical weaknesses
-
ReL-WM receives simulator-derived graphs during both training and execution. These graphs use object poses, contact forces, and grasp predicates. The paper does not include a baseline given the same information without the proposed relational dynamics. Removing the semantic branch also removes the graph input, so that ablation does not isolate the benefit of predicting relations. The lighting results are similarly difficult to interpret because simulator-derived relations remain available when images become harder to read.
-
The real-robot experiments do not yet resolve this concern. Appendix A.1 evaluates an imitation policy trained on frozen world-model features, rather than the proposed imagination-based RL agent. It also does not clearly explain how the real-robot graphs and progress labels are obtained during training and execution. These details are needed to understand what information the deployed policy requires and how practical the approach is outside simulation.
Questions for authors
-
How does ReL-WM compare with DreamerV3 given the same simulator information or graph embeddings, but without a separate relational dynamics model? Can you retain graph input while removing only relational prediction?
-
How are scene graphs constructed in the real-robot experiments? Which quantities are measured, estimated, or manually annotated, and which are needed at inference?
-
Which parts of the progress schedule are generated automatically from the five demonstrations?
-
Do the main ablation results hold beyond PlaceSphere, particularly on peg insertion or mobile manipulation? It would also help to test missing objects or incorrect grasp states, beyond changing relation labels to neighboring categories.
5 comments
Gentle Reminder
Dear Reviewer yQup,
We hope this message finds you well. We try to address your concerns. Should there be any concerns or points you wish us to clarify further? Please do not hesitate to reach out. We are more than willing to extend our conversation and eagerly anticipate any further discussions that may arise.
Best regards,
All Authors
Gentle Reminder
Dear Reviewer yQup,
We hope this message finds you well. We understand that you are busy with revision for your paper, but can you spend a little time to check out our rebuttal ? This work is very important for us too. We are more than willing to extend our conversation and eagerly anticipate any further discussions that may arise.
Best regards,
All Authors
Thank you for your detailed, thoughtful, and constructive review. We address your questions and concerns below, and all locations refer to the revised PDF.
Q1 / W1. Additional baseline. We added two baselines with matched graph information.
Tables 3 and 8 report the comparisons, summarized below
Both variants remain below ReL-WM on every task, so access to the graph does not by itself explain the gain. Under both MS-HAB lighting changes, both matched variants receive the same graphs as ReL-WM, ReL-WM still leads, and its gap to ReL-WM w/o semantic branch widens (Table 8, Page 19, Line 973, and Page 20, Lines 1030–1032).
Q2 / W2. Real-robot scene graphs. A VLM takes the place of the simulator, and no quantity is annotated manually (Page 15, Lines 787–797).
ReL-WM also predicts the VLM-labelled relations of the held-out robot demonstrations more accurately than both matched variants and a persistence baseline (Table 11, Page 21, Line 1114).
Q3. Automatic progress schedule. Every stage is generated automatically, and Table 17 (Page 30, Line 1567) lists each stage with its input and output.
The labelling prompt and its output format are included in Appendix A.1 (Page 15, Line 805 to Page 18, Line 918), and Appendix D lists the generated schedules (Page 41, Line 2206).
Q4. Ablations beyond PlaceSphere and graph errors.
Tables 3 and 9 report the ablations, summarized below
On all three tasks, predicting progress without shaping improves over removing progress, and shaping adds a further gain. With corrupted graphs, ReL-WM still outperforms DreamerV3 + flat graph with clean graphs on all three tasks.
We hope that these results address your concerns, and we would be grateful if you would reconsider your score.