- Rating
- 4(+1)
- Confidence
- 4
- Informativeness
- 3
- Presentation
- 3
- Soundness
- 3(+1)
Read review
Paper summary
This paper investigates the limitations of Euclidean distance as a terminal cost for goal-conditioned planning with latent world models and proposes Neighborhood Graph Cost (NGC) as an alternative. The authors observe that Euclidean distances in LeWM representations are informative only within local neighborhoods and can produce misleading low-cost regions for distant goals, despite the latent representations retaining task-relevant state information. To address this issue, NGC constructs a mutual nearest-neighbor graph from encoded training observations and estimates distances between predicted terminal states and goals using shortest paths along the graph. The method replaces only the planning cost and requires no additional model training. Experiments across four continuous-control tasks demonstrate substantial improvements over Euclidean latent distance, particularly for longer goal horizons. Additional ablations, oracle-predictor evaluations, computational comparisons, and experiments with alternative checkpoints and representations support the effectiveness of the approach while highlighting its dependence on neighborhood quality.
Critical strengths
-
The paper presents a well-motivated approach to addressing the mismatch between Euclidean latent distance and task-relevant progress in goal-conditioned planning. By replacing only the terminal cost with a graph-based distance, NGC achieves substantial improvements across four continuous-control tasks while keeping the world model and planner unchanged. The gains are particularly significant at longer goal offsets, where Euclidean distance becomes less informative. The evaluation using released LeWM checkpoints further supports the robustness of the main findings. The simplicity of the proposed intervention and its strong empirical performance make this a practically meaningful contribution.
-
The paper provides several useful experiments beyond the main performance comparisons. In particular, the shortest-path ablation demonstrates that the improvements primarily arise from graph-based path distances rather than local density corrections or nearest-neighbor attachment alone. The oracle-predictor experiments help distinguish the limitations of the terminal cost from world model prediction errors, while the CEM budget comparison shows that simply increasing the search budget does not eliminate the performance gap. The authors also investigate alternative representations, graph sensitivity, and failure cases in contact-rich environments. These analyses provide relatively strong evidence for the proposed explanation while acknowledging its practical limitations.
Critical weaknesses
-
Although the paper reports relatively modest online planning overhead, NGC requires constructing a neighborhood graph and precomputing all-pairs shortest-path distances, which introduces additional offline computation and quadratic storage complexity. Appendix H reports approximately 100 MB for the distance table with 5,000 graph nodes, but the preprocessing time, peak memory consumption, and scaling behavior for substantially larger graphs are not fully evaluated. Since a sufficiently dense graph may be necessary to preserve local manifold structure in complex environments, understanding these costs is important for assessing the practicality of NGC beyond the relatively small graphs considered in the current experiments. A more comprehensive scalability analysis would strengthen the paper's claims regarding computational efficiency.
-
The proposed method assumes that nearby latent representations correspond to meaningful local relationships in the underlying environment, but this property is not guaranteed across different world model architectures or data distributions. The LpWM experiments provide useful evidence of this dependence, showing that NGC yields limited improvements on Cube and PushT when local neighborhoods are less faithful to physical state geometry. Moreover, the graph-size and neighborhood-size ablations reveal substantial performance degradation under insufficient coverage or overly large neighborhoods, particularly at longer goal offsets. Although the paper acknowledges these limitations, its evidence remains concentrated on closely related latent world model representations. Further validation on different representation families would help establish when the manifold-based cost is reliable and when graph construction may introduce misleading connections.
Questions for authors
-
How does the computational cost of NGC scale with the number of graph nodes? Appendix H reports the storage requirements of the precomputed shortest-path table and relatively modest online latency at the evaluated graph sizes. Could the authors extend the graph-size experiments to report offline graph construction time, all-pairs shortest-path preprocessing time, peak memory consumption, and online planning latency as the number of nodes increases? Since the method relies on a quadratic distance table, understanding its computational behavior at larger scales would materially affect my assessment of its practical applicability.
-
How well does NGC generalize to world models with different representation-learning strategies? The additional LpWM experiments provide valuable evidence that NGC's effectiveness depends on the fidelity of local latent neighborhoods. However, LeWM and LpWM remain relatively closely related representation-learning frameworks. Could the authors evaluate NGC on a world model using frozen pretrained visual representations, such as DINO-WM, while keeping the model and planning budget fixed? Reporting both L2 and NGC performance together with local neighborhood-quality measurements would help clarify whether the proposed approach generalizes beyond the evaluated representations and identify the conditions under which graph-based distances are reliable.
4 comments
Response to Reviewer fR7J (Part 2/3)
W2 / Q2:
The proposed method assumes that nearby latent representations correspond to meaningful local relationships in the underlying environment, but this property is not guaranteed across different world model architectures or data distributions.
Further validation on different representation families would help establish when the manifold-based cost is reliable and when graph construction may introduce misleading connections.
Could the authors evaluate NGC on a world model using frozen pretrained visual representations, such as DINO-WM, while keeping the model and planning budget fixed? Reporting both L2 and NGC performance together with local neighborhood-quality measurements would help clarify whether the proposed approach generalizes beyond the evaluated representations and identify the conditions under which graph-based distances are reliable.
Thank you for this insightful suggestion. We agree that NGC relies on meaningful local relationships in latent space, which are not guaranteed across representations or tasks. If physically distant states are mapped close together, NGC can inherit misleading connections rather than correct them, limiting its benefits over L2.
Following your suggestion, we evaluated NGC on the DINO-WM checkpoints released by Point-LeWM, which use frozen DINOv2 features and task-specific predictors trained on the four environments. We kept the model, evaluation pairs, and planning budget fixed between L2 and NGC. To further remove the influence of prediction errors, we also evaluated an oracle predictor at the longest offset. Entries below show L2 → NGC success rates (%):
| Task | Offset 25 | Offset 50 | Longest offset | Longest offset, oracle |
|---|---|---|---|---|
| TwoRoom | 100 → 100 | 96 → 98 | 62 → 80 | 56 → 100 |
| Reacher | 94 → 100 | 100 → 100 | 94 → 100 | 94 → 100 |
| Cube | 48 → 58 | 44 → 44 | 50 → 54 | 68 → 70 |
| PushT | 74 → 70 | 46 → 46 | 12 → 14 | 12 → 18 |
These results show that NGC remains effective on TwoRoom and Reacher with frozen DINOv2 representations, while its gains on Cube and PushT are limited. This pattern is similar to what we observe with LpWM.
We also appreciate your suggestion to report local neighborhood quality alongside planning performance. We quantify neighborhood quality using the mean operational physical distance to the 15 nearest neighbors in latent space. Lower values indicate more physically local neighborhoods. Entries below report mean distance / longest-offset oracle L2 → NGC success (%):
| Task (distance unit) | LeWM–Oracle | LpWM–Oracle | DINOv2–Oracle |
|---|---|---|---|
| TwoRoom (px) | 3.14 / 19 → 100 | 3.27 / 60 → 100 | 3.25 / 56 → 100 |
| Reacher (rad) | 0.1284 / 80 → 100 | 0.1356 / 94 → 100 | 0.1757 / 94 → 100 |
| Cube (cm) | 13.94 / 37 → 73 | 18.66 / 34 → 38 | 15.79 / 68 → 70 |
| PushT (px) | 111.75 / 13 → 38 | 140.96 / 8 → 6 | 148.23 / 12 → 18 |
On Cube and PushT, the representations used by LpWM and DINOv2 indeed have poorer local neighborhood quality than LeWM, corresponding to their smaller improvements from NGC over L2.
Continued in the next comment with additional AntMaze results.
Response to Reviewer fR7J (Part 3/3)
Response to W2 / Q2 (continued)
To further examine whether NGC’s benefits beyond LeWM extend to more complex tasks, we additionally evaluated visual AntMaze from OGBench, where an eight-actuator quadruped must coordinate locomotion and repeated foot–ground contacts while navigating around walls. We did not find an available DINO-WM checkpoint for this task, and training one was beyond our rebuttal time budget. We therefore evaluated frozen DINOv2 features only with an oracle predictor.
| Representation | Predictor | Mean distance (m) | Offset 25 | Offset 50 | Offset 100 |
|---|---|---|---|---|---|
| LeWM | Learned | 0.353 | 58 → 100 | 40 → 98 | 44 → 90 |
| LeWM | Oracle | 0.353 | 56 → 100 | 40 → 100 | 40 → 100 |
| LpWM | Learned | 0.356 | 86 → 100 | 62 → 94 | 52 → 92 |
| LpWM | Oracle | 0.356 | 86 → 100 | 60 → 100 | 46 → 100 |
| DINOv2 | Oracle | 2.778 | 78 → 94 | 60 → 66 | 46 → 52 |
Interestingly, unlike the pattern across the other four tasks, LpWM and DINOv2 behave quite differently on AntMaze. Both LpWM and LeWM have good neighborhood quality and benefit substantially from NGC, whereas DINOv2 has considerably poorer neighborhood quality and gains much less.
We acknowledge that NGC is not highly effective across all representations and tasks. Nevertheless, its benefits are not confined to the LeWM framework or to relatively simple tasks such as TwoRoom and Reacher. Understanding why different representation-learning strategies produce different neighborhood quality is a challenging and interesting question that we intend to investigate further. Although we do not yet fully understand the underlying causes, we believe that these results, showing how NGC’s effectiveness varies across representations and tasks, are valuable to share with the community. They may motivate further discoveries and methods that improve upon NGC. As suggested by our paper’s title, our central message is to offer a manifold perspective on planning with latent world models, with NGC serving as a concrete method for exploring this perspective.
Summary
Thank you for guiding us toward experiments that strengthen both the practical case for NGC and our understanding of when it helps. They show modest overhead at the tested scales and benefits beyond the originally evaluated representations, including frozen pretrained features. The extent of these benefits varies with the task and representation-learning strategy, raising intriguing questions about the underlying mechanisms. We will incorporate these results and their implications for planning into the final paper. Please let us know if any concerns remain or if further clarification would be helpful during the discussion.
Thank you for the additional experiments and clarifications. The scalability measurements clarify the practical costs at the evaluated graph sizes, while the DINO-WM and additional AntMaze experiments broaden the empirical support beyond the original settings. I also appreciate the neighborhood-quality analysis, which helps explain both the gains and the limitations across representations. My main concerns have been satisfactorily addressed. Given the paper’s useful insight, simple approach, and strengthened empirical evidence, I am raising my score from 3 to 4.
Response to Reviewer fR7J (Part 1/3)
We appreciate your constructive review and valuable suggestions. Below is our detailed response to your questions and comments.
Thank you for raising this question regarding the practical applicability of NGC. We extended the graph-size experiments on TwoRoom and Cube to report all four requested costs:
Measurements use an A100 40GB GPU and one numerical CPU thread, with three graph draws and three repeats per graph. Graph construction starts from encoded nodes, memory is the preprocessing worker's peak CPU RSS, and online latency covers a complete CEM solve.
When considering how these costs affect practical use, we would like to invite you to distinguish between one-time offline preprocessing costs and online deployment costs. We believe the offline costs have little impact on practical applicability: although graph construction and APSP scale as O(N2logN), they are performed only once for a fixed representation and graph. Like model training, this work happens before deployment and adds only a tiny fraction to the time needed to prepare the model for use: at 10,000 nodes, the two steps together take only 80–90 seconds. Compared with the 5.37 hours required to train the corresponding TwoRoom model on an RTX 4090, the graph and APSP computation is only 0.41% of that recorded training time. Moreover, if preprocessing RAM becomes limiting at larger scales, blockwise computation and disk-backed storage can reduce the memory requirement at the expense of additional preparation time.
Online latency and memory have a more direct impact on practical use because they determine how efficiently planning can run on the deployment hardware. Fortunately, the online scoring work scales as O(NlogN), rather than quadratically, and remains very small relative to world-model prediction: even at 10,000 nodes, a complete CEM solve takes approximately 609 ms, only 5.4% above L2 on both tasks.
Online memory does not need to scale quadratically either: rather than keeping the Θ(N2) distance table in RAM or GPU memory during planning, we only need to pay a small setup cost whenever the goal changes to extract a goal-specific vector of length N. Although the full FP32 table occupies 100 MB at 5,000 nodes and 400 MB at 10,000 nodes, planning toward a fixed goal only requires each node's distance to that goal through its anchors. When the goal changes, we read the distance rows for its four anchors from disk, add each anchor's distance to the goal, and take the minimum for each node. The result is a vector of length N, occupying only 0.02 MB for 5,000 nodes and 0.04 MB for 10,000 nodes, so each candidate can be scored using its distances to its own anchors and the cached anchor-to-goal values. With the full table kept on disk, finding the goal anchors and constructing this vector took median times of 6.5 ms on TwoRoom and 9.2 ms on Cube at 10,000 nodes in a CPU microbenchmark on our shared filesystem (p95: 41 and 237 ms). This setup cost is paid only when the goal changes, while all subsequent planning calls reuse the vector and require only linear O(N) distance storage in memory. We will include these scaling results and discussion in the revised manuscript.