- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
This paper studies loss of plasticity in continual robot learning from visual observations, and shows that using a Skewon optimizer rather than AdamW can be a good mitigation to this problem. The Skewon optimizer enforces orthogonality in DNN matrices, and therefore, regularizes the network and prevents the pathological behavior that are caused by saturated ("dead") neurons. The authors relate plasticity to norm of Jacobians, and showed that on a controlled LQR task, Skewon gives larger and a stable norm of Jacobians, while AdamW can span a wide distribution. Finally, they showed that their optimizer made improvements over AdamW on four continual locomotion settings, and two simulated manipulation chains, and a sequential behavior-cloning fine-tuning of SmolVLA’s action expert on a physical SO-101 robot.
Critical strengths
- The paper addresses an important problem: maintaining the ability to adapt during continual learning for robots. The evaluation spans a controlled setting, simulated locomotion and manipulation, and physical hardware.
- Improvements on the SO-100 Cup-Align task are substantial. Skewon achieved 92% compared to 3% with AdamW, while both optimizers have similar performance when learning the task from scratch.
Critical weaknesses
- I'm not convinced that the Jacobian evidence establishes the proposed explanation of plasticity. First of all, section 3.1 is confusing because it is not the setup that later experiments use. So why mentioning this setup? The setup does not provide evidence to support their argument either; input sensitivity is not equivalent to trainability on a new objective. A larger Frobenius norm need not imply better conditioning or preservation of useful directions.
- Stiefel optimization and Skewon are existing methods, so the contribution of this paper is limited to assess their performance in visual-control studies.
Questions for authors
- Can you clarify the role of the setup in section 3.1? Is the Jacobian discussion intended as an intuitive motivation, an empirical hypothesis, or a theoretical explanation of the method’s effectiveness? Clarifying this distinction would help establish what the subsequent experiments are intended to validate.
- Section 3.2 describes established Stiefel optimization methods and the existing Skewon optimizer. Could the authors state more explicitly which methodological components are new, distinguishing the application of Skewon to continual visual control from the Gram-Skewon extension? What additional insight does the empirical study establish beyond the previously observed benefits of orthogonality-based regularization?
- Can the authors provide within-chain LQR learning trajectories, relating the Jacobian measured before adaptation to subsequent learning performance? How does the interpretation change when the Jacobian is measured on a common observation set?
4 comments
Continued Response to Reviewer Bgcs
within-chain LQR learning trajectories relating the Jacobian measured before adaptation to subsequent learning performance
We show how the LQR learning trajectories and the Jacobian norm, over a common observation set, decays as the return also decays for Adam optimizer (figure 7 in Appendix of in the latest version). We also present the condition number and show how the input-output Jacobian becomes ill-conditioned as training progresses under AdamW. This does not happen for Skewon. Note that this need not always be true meaning for some randomly sampled task chains the performance does not drop as the chain progresses with AdamW optimizer. This is simply because some LQR tasks are too easy to solve and their performance need not degrade even if they are later in the chain.
We hope our response and new experiments have addressed your concerns. Please let us know.
References:
[1] Andries Rosseau, Robert Muller, and Ann Nowe. Preserving plasticity in continual learning via dynamical isometry.
[2] Arslan Chaudhry, Naeemullah Khan, Puneet K. Dokania, and Philip H. S. Torr. Continual learning in low-rank orthogonal subspaces.
[3] Wesley Chung, Lynn Cherif, David Meger, and Doina Precup. Parseval regularization for continual reinforcement learning.
Thanks for addressing my questions, but I'm not fully convinced by the author's response.
The re-write of section 3.1 seems to be a paraphrase of Rosseau et al. (2026). I still don't think a smaller condition number or a larger norm of the Jacobian implies higher plasticity. This is too general a statement to provide any scientific insight.
With that, the novelty of the paper seems to be limited to testing a pre-established optimizer (with slight variants) on some new tasks designed by the authors. I will keep my score.
Response to Reviewer Bgcs
Thank you for your continued engagement with our work.
Jacobian and Section 3.1: We present the work of Rosseau et al. (2026) in the background section. This is intended to be informative of the past work and keep our paper self contained. It is not a contribution of ours and our conclusions do not depend on it. We will remove the Jacobian line from the abstract and also shorten Section 3.1 in response.
The scientific insight is maintaining a hard Stiefel constraint mitigates loss of plasticity. This is building on past work as does most research.
Novelty: We respectfully disagree with you on this. The Gram-Skewon is not a slight variant. It is a new contribution for adapting pre-trained networks. Skewon requires , so it cannot be applied to a pretrained network without altering it. Gram-Skewon holds at its pretrained value. It requires a different inverse-free retraction (Appendix D). This is the setting of real-world fine-tuning. It also improves final-task success from 37% to 62% on a physical robot
We present a comprehensive results on tasks designed to test plasticity, including a real robot. These are first of their kind results for robotic control from pixels and are building towards solving an important problem: agents that can continually learn and adapt in ever-changing environments.
We hope you will reconsider your score in light of these clarifications.
Response to Reviewer Bgcs
Thank you for your detailed review of our work and pushing us to clarify and improve our work. We address your concerns below.
The Jacobian discussion is intended for intuitive motivation. Ours is primarily empirical work based on the previous theoretically grounded work [1,2,3]. The simple feed-forward network in Section 3.1 is used only to define the input-output Jacobian J(x)=∂F(x;W1,…,WL)/∂x; in our experiments we measure the Jacobian of the policy with respect to its observation.
Building on the theory by Rosseau et al [1] we argue that maintaining the invariant property W⊤W=I potentially improves the conditioning. We introduce this to set the stage for the correlation between the Jacobian norm and plasticity. We have updated the writing for 3.1 and lead with the following explanation:
Rosseau et al. (2026) denote the empirical neural tangent kernel (NTK) as Kθ(X)=Jθ(X)Jθ(X)⊤, where Jθ(X)=∂F(X;θ)/∂θ is the Jacobian with respect to the parameters. The first-order change in loss under a task-gradient g at task index τ is ΔLτ=−ηg⊤Kθ(Xτ)g+O(η2), where η is the learning rate, Lτ is the loss for task τ, and Xτ is the input dataset for task τ. Ensuring that the learning rate satisfies η≲1/λmax(Kθ(X)), so that learning remains convergent, the worst-case decrease in loss for unit-norm task-gradient directions is:
λmax(Kθ(X))λmin(Kθ(X)),
which is maximised exactly when λmin=λmax, i.e. when Kθ(X) is isotropic. Their conclusion is that the condition number of Kθ(X), and not its magnitude, determines task-agnostic plasticity, since η is bounded by 1/λmax(Kθ(X)) and learning is slowest along the directions of λmin(Kθ(X)).
Their Section 2.3 connects this to the input-output Jacobian: under a task-agnostic input prior with E[XX⊤]=In, a dynamically isometric network, one whose input-output Jacobian singular values remain concentrated near one, has an empirical NTK that concentrates near isotropy in expectation.
We agree that a larger Jacobian norm need not imply better conditioning. We therefore additionally report the condition number κ(J)=σmax(J(x))/σmin(J(x)) over the non-zero singular values for the LQR chains (Figure 7 in the Appendix). Under AdamW, κ(J) rises along the chain while σmax(J(x)) stays nearly constant, so σmin(J(x)) approaches zero and ∥J(x)∥F declines with it. Moreover, we show how the two change together: as the condition number increases the Jacobian norm decreases. We also test trainability on a new objective directly: checkpoints from the Skewon chain adapt to a held-out task far better than AdamW checkpoints (Table 2).
We are now intuitively explaining this in Section 3.1. We do not provide detailed theory as ours is not theoretical work.
We have two main methodological contributions: We present first end to end results for continual learning from frames for MuJoco and ManiSkill tasks with tens of millions frames. This empirical calibration of hyper-parameters and application of a new optimizer is substantial and opens up avenues of research as well as applications. We have also introduced chains of tasks for robotic control and continual learning. These are first of their kind empirical results. We extend the Skewon algorithm to present Gram-Skewon optimizer for the pre-trained VLAs (Section 6) where we cannot ensure the property: W⊤W=I. This optimizer ensures that for a large pre-trained network the quantity W⊤W remains invariant even if it is not equal to identity. We also show that this works on a real robot.
Not only are these important empirical results but we also present a novel optimization based perspective for maintaining plasticity.
Additionally, we observe that maintaining a hard constraint performs better than regularisation, as shown by our experiments. The revised Table 1 compares two ways of using orthogonality on the same chain: Parseval [3] regularises towards it, and Skewon enforces it as a hard constraint. While our work builds on the results of Chung et al [3], we see stark improvements in comparison by introducing a hard constraint. These are now detailed in the introduction (lines 70 to 91), the empirical section, and the entire discussion section. We hope this addresses your concern.