- Rating
- 2(+1)
- Confidence
- 4(+1)
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper presents JACT, an offline goal-conditioned policy optimization method using JEPA for future embedding alignment and consequence training. It shows improvement compared to GC-IDM in some tasks and reduces the deployment consumption compared to online planning methods.
Critical strengths
None.
Critical weaknesses
-
The novelty of the method proposed is limited. This is basically an offline model-based imitation where policy is optimized towards alignment between predictions and observed future embeddings. This framework resembles [1]. The waypoint prediction in 3.2 is incremental since decoder preserves states and goals, and it supposes that task progression is near linear and limits its applicability to non-linear progressed tasks.
-
The results in Tab.1 is mostly dependent on reported results but not reproduced results. Comparable baselines only include one method (GC-IDM) which is totally insufficient. Improvements in Tab.2 also seems marginal as is in the error bar. Ablations in Tab.3 seems not consistent especially on Cube-double task. Results in Fig.2 lacks error bar across seeds. Direct control degrades from 99/65 to 30/32 compared to CEM as reported in 4.5, which does not compensate for the decision budget that is saved. Related to Q2, ablation on waypoint prediction is missing.
-
The writing is overall tedious with over-detailed descriptions on prior knowledge. There are numerous notations which contain actually little information which makes the paper hard to follow. Fig.1 is basically AI-generated and contains meaningless text. The ablations in 4.3 require more detailed descriptions on experimental setup, model modifications, etc. Lastly, the paper needs to adjust the header and "manuscript in preparation" which seems to be totally not ready to me.
[1] Mitigating Covariate Shift in Imitation Learning for Autonomous Vehicles Using Latent Space Generative World Models
Questions for authors
-
What distinguishes JACT from model-based imitation learning with differentiable trajectory matching?
-
What about removing the waypoint prediction in eq.7? How much does it contribute to the final performance?
-
Results in Tab.2 is selected among epochs 1-10, how sensitive is the comparison to this selection? It would be helpful if scores among epochs are presented.