- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
JEPA-Bisim projects frozen visual features into a smaller patch-level latent space and jointly trains action-conditioned dynamics with a reward-free bisimulation-inspired loss. A PCA-based variance/covariance regularizer is intended to prevent collapse while permitting removal of dominant nuisance directions. Planning uses CEM with terminal latent distance. Experiments on PointMaze and PushT evaluate robustness to background changes and distractors, with additional visual-encoder comparisons. The paper also proposes an on-policy cost-to-go bound as a theoretical justification for invariance.
Critical strengths
-
The robustness problem is relevant. Frozen visual features can retain nuisance variation, so adapting the representation used by a planner is a reasonable direction. Testing background shifts and distractors directly addresses the intended failure mode.
-
The implementation is modular and compact. A patch-wise projection preserves spatial structure while reducing each DINOv2 patch from 384 to 32 channels, allowing the approach to be used with several pretrained encoders.
-
PointMaze shows encouraging robustness. Table 1 reports 78% native success and small changes under the tested shifts for DINO-Bisim, whereas the DINO-WM baseline degrades substantially under several background changes. The paper includes a domain-randomization baseline and acknowledges that lower relative degradation need not mean higher absolute success.
Critical weaknesses
-
Theorem 3.1 is false under its stated approximate-preservation assumption. The assumption permits representation-distance error up to epsilon, but the bound contains no epsilon term. Consider two states with identical transitions, hence zero reward-free bisimulation distance, and scalar representations h(z) = 0 and h(z') = delta, where 0 < delta <= epsilon. With goal representation zero and T = 1, the assumed approximation and boundedness hold, yet the cost difference is delta squared while Equation (5) bounds it by zero. A corrected theorem needs an approximation term and explicit metric assumptions. Moreover, a fixed-policy cumulative-cost bound does not directly guarantee the terminal-cost CEM planner's decisions.
-
The practical target is not justified as a Wasserstein bisimulation estimator. Independently sampled next states form a product coupling, not generally the optimal coupling required by Wasserstein distance. Even identical transition distributions can have positive expected distance between independent draws, although their Wasserstein distance is zero. The standard recursive metric also specifies the ground pseudometric (Castro, 2020); the paper leaves this unclear. With no reward or other distinguishing term, the usual discounted recursive construction admits the all-zero bounded fixed point. Anti-collapse regularization can create useful features, but does not establish the claimed control equivalence, especially for actions outside the behavior policy.
-
Relative robustness hides a large absolute control-performance loss on PushT. With full data, native success falls from 78% for DINO-WM to 44% for DINO-Bisim. Converting the rounded relative degradations in Table 2 gives approximately 66.3% versus 44.0% success under SC and 49.9% versus 37.8% under LC. DINO-Bisim is worse on four of the five shifted conditions in this full-data setting, although its relative degradation is smaller. Thus, the main manipulation result does not demonstrate a generally better robust planner.
-
The contribution of bisimulation is not isolated in the available experiments. Compact projection, predictive training, bisimulation loss, and PCA-based regularization all change together. Matched 32-dimensional dynamics without bisimulation, standard variance/covariance regularization, and PCA-only controls are needed. Figure 4 does not establish that the dominant component is always nuisance: scene layout may be essential for obstacle avoidance. The exact PCA loss and the referenced ablations are deferred to an appendix absent from the supplied PDF.
-
The empirical scope and uncertainty are limited. Evaluation covers two environments with 50 initial-goal pairs per condition, without reported repeated-training variation or paired intervals. This makes small improvements such as negative relative degradation difficult to interpret. Dimension reduction alone also does not establish an equivalent reduction in complete planning latency.
Questions for authors
- How is the T = 1 counterexample excluded by the stated assumptions of Theorem 3.1? Please supply the proof and a corrected bound with explicit approximation dependence.
- What ground metric defines the Wasserstein term, and what justifies independent action/transition pairs as its estimator? How is off-policy action distinguishability preserved for CEM?
- Can you report absolute success under every shift, with uncertainty, and explain the 78% to 44% native-performance drop on full-data PushT?
- Which gains remain against matched compact predictive models and PCA/variance regularization without the bisimulation term?
4 comments
Point-to-point response to Reviewer GReR (2/2)
6. Scope, uncertainty, and planning latency.
As discussed in the general response and our response to Reviewer 2Xdi (point 7), we evaluate initial-goal pairs per condition following the same evaluation protocol as DINO-WM.
The additional Wall evaluation is reported in our general response.
Our compactness claim relies on latent dimension: is reduced to , exactly fewer coordinates. We will clarify that this does not imply a measured reduction in total planning latency, however, it yields to planning on a much more compact latent space.
Dear Reviewer,
We would like to follow up on our responses to your concerns and questions and kindly ask you to adjust your score if your concerns/question have been addressed. Thank you!
Dear Reviewer,
We thank you for your time reviewing our work. We are happy to discuss any additional question you may have. If our responses have addressed your questions and concerns, we would appreciate if the score can be adjusted accordingly. Thank you!
Point-to-point response to Reviewer GReR (1/2)
We thank the Reviewer for recognizing the relevance of guaranteeing robustness to distractors and background changes at test-time. And also for recognizing our compact and modular patch-wise encoder, and the PointMaze results, including the domain-randomization comparison. We address all five weaknesses and the corresponding questions below.
1. Theorem 3.1 and the T=1 counterexample.
The counterexample is valid under the stated assumptions. An additive distance approximation permits d(z,z′)=0 while ∣∣hη(z)−hη(z′)∣∣2>0. The cost difference therefore cannot be bounded by a multiple of d(z,z′) alone. We correct the statement and Appendix A.11.
Our response to Reviewer 2Xdi, point 2, provides the corrected statement and proof. For a specified pseudometric d, Wd(Pπ(⋅∣z),Pπ(⋅∣z′))≤Ld(z,z′), bounded embeddings, and ∣∣hη(z)−hη(z′)∣∣≤d(z,z′)+ε,
\leq4H_ w\left[\sum_ {t=0}^{T-1}(\gamma L)^t d(z,z')+ \varepsilon\sum_ {t=0}^{T-1}\gamma^t\right].$$ At $T=1$ and $d=0$, the bound is $4H_w\varepsilon$, rather than zero, so it covers the suggested counterexample. Under $\gamma L\leq1$, the corrected bound retains the original $T d(z,z')$ dependence. For fixed $0\leq\gamma<1$, the added term is at most $4H_w\varepsilon/(1-\gamma)$, so it vanishes as $\varepsilon \to 0.$ **2. Ground metric, independent pairs, and off-policy actions.** Our objective uses transition-distance supervision to adapt pretrained features jointly with action-conditioned prediction and anti-collapse regularization. The target in Section 2.3 is $$\gamma||T_ \phi(w,a)-T_ \phi(w',a')||_ 2.$$ Independent transition pairs provide a tractable comparison signal, but do not generally realize the optimal Wasserstein coupling. For exact successor samples and ground pseudometric $\rho$, $$W_ \rho(P_ \pi(\cdot\mid z),P_ \pi(\cdot\mid z')) \leq \mathbb E[\rho(U,V)],$$ with equality only when the independent coupling is optimal. We therefore describe this term as a *bisimulation-inspired transition-distance regularizer*, rather than an exact Wasserstein estimator. This preserve the reward-free learning procedure and its empirical robustness results while stating precisely what the objective establishes. **3. Relation to terminal-cost CEM planning.** As detailed in our response to Reviewer 2Xdi (point 3), the argument extends to the terminal objective. For every common candidate sequence $\boldsymbol a$, $$|J_ z(\boldsymbol a)-J_ {z'}(\boldsymbol a)| \leq 4H_ w[L^Td(z,z')+\varepsilon].$$ Thus, when two observations have small distance $d(z,z')$, the same candidate action sequence has similar expected terminal costs from either observation, up to the representation approximation error $\varepsilon$. We will include this extension in the revision. **4. Absolute PointMaze and PushT performance.** The revised paper reports absolute success for every condition in Table 1 (PointMaze), Table 2 (matched-width PushT), and Appendix A.12 (PushT training-data ablation). The compact model has lower native success on PushT, particularly with the full dataset. With $1{,}000$ samples, increasing DINO-Bisim's width from $32$ to $384$ raises native success from $36$\% to $40$\%. At matched width, DINO-Bisim improves absolute success under every shift, with native success of $40$\% versus $48$\% for DINO-WM. See the new PushT table in our general response. The additional Wall results (see our general response) further show higher absolute success on all five selected patterned backgrounds, with comparable native success ($90$\% versus $92$\%). **5. Component attribution, PCA, and layout information.** The appendix is included in our **submitted supplementary materials**. In particular, Appendix A.3 presents the PCA objective and visualizations of the learned representations before and after the regularization. Appendix A.10 evaluates seven planning horizons. and Table 1 compares DINOv2, SimDINOv2, iBOT, and end-to-end training. This evaluates representation learning metrics, planning horizon, and encoder choice. The ablation table in our general response adds the compact projector, PCA-only, and bisimulation ablations, with all metrics defined there. Our objective is to suppress changes in appearance that leave the physical task unchanged. Obstacle geometry must remain available to the planner because it determines feasible motion. The PCA visualizations concern the tested background variations and do not establish that PC1 is universally control-irrelevant. As clarified in our response to Reviewer 2Xdi, the implementation uses a fixed PCA basis with explicit variance targets, together with covariance regularization in the original per-patch coordinates. We will make this more clearer in our revision.