- Rating
- 3
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
HIJP jointly trains a visual encoder, forward dynamics, and a goal-conditioned inverse head. The inverse head learns the immediate action toward sampled future observations, while a cycle objective checks that this action predicts the observed next state. At inference, alternating inverse and forward predictions produces an action sequence without iterative search. Four benchmarks evaluate success across increasing goal distances, with component ablations and timing comparisons.
Critical strengths
-
The coupling is coherent and reasonably well isolated. Table 3 tests future-goal sampling, gradients through the goal representation, the cycle loss, and replacing direct inference with CEM on the same representation. These controls provide useful evidence beyond comparing separately trained systems.
-
The manipulation results are promising: Table 1 reports overall success of 86.8%, versus 81.9% for INTACT, with particularly strong difficult-goal results on PushT and OGCube. Table 2 also demonstrates a substantial runtime advantage over the evaluated CEM planner under matched replanning schedules.
Critical weaknesses
-
The reliability and generalization of the success gains need clearer evidence. Each task and difficulty cell uses 50 evaluation instances. Appendix A.1 splits overlapping training windows into training and validation sets, while A.2 samples evaluation starts from offline trajectories. This does not establish leakage, but the relationship between training trajectories and evaluation episodes is insufficiently explicit. The 4.9-point aggregate advantage should be supported by paired uncertainty estimates and a clear episode-level holdout protocol.
-
The efficiency evidence is narrower than the comparison to existing planning methods suggests. Timing uses batches of 50 episodes and a CEM configuration with 300 candidates and 30 iterations; the closest search-free baseline, INTACT, is not timed. Success also does not improve uniformly, notably on Reacher. A success-versus-runtime comparison across CEM budgets and against INTACT would clarify the practical advantage.
Questions for authors
-
Are evaluation trajectories or initial/goal observations disjoint from training at the episode level? Please specify the episode-level split and which observations are available during training.
-
Can you compare total planning latency and success against INTACT and several CEM budgets, at batch size one as well as 50, under the same replanning schedule?
5 comments
Response to Reviewer oBJe (Part 2)
Q2: What is the paired uncertainty around HIJP’s reported 4.9-percentage-point aggregate advantage over INTACT, given 50 evaluation episodes per task and difficulty level?
A2: To quantify paired uncertainty, we used Push-T, where both methods were trained with three training seeds under the trajectory-level holdout protocol. Within each training run, HIJP and INTACT were evaluated on identical start–goal pairs (3 evaluation seeds × 50 pairs per level). We report HIJP − INTACT success-rate differences in percentage points, with 95% paired bootstrap confidence intervals obtained by resampling start–goal pairs within each evaluation seed (20,000 resamples).
| Training seed | Easy | Default | Hard | Extreme | Avg. |
|---|---|---|---|---|---|
| 0 | −3.3 [−8.0, +0.7] | −2.7 [−10.0, +4.0] | +9.3 [−0.7, +19.3] | +17.3 [+8.7, +26.0] | +5.2 [+1.2, +9.0] |
| 42 | −6.0 [−10.7, −2.0] | −0.7 [−8.0, +6.7] | +5.3 [−4.7, +14.7] | +13.3 [+4.0, +22.0] | +3.0 [−1.0, +6.8] |
| 3072 | −2.0 [−7.3, +3.3] | +11.3 [+2.7, +20.0] | +10.7 [+0.7, +20.7] | +29.3 [+20.7, +38.0] | +12.3 [+8.2, +16.5] |
The paired difference in the four-level average was positive in all three training runs (+5.2, +3.0, and +12.3 percentage points), and its confidence interval excluded zero in two of the three runs. The advantage was concentrated at Extreme, where the confidence interval excluded zero in every run (exact McNemar test, p ≤ 0.008). At Easy, INTACT achieved higher success in all three runs, with the confidence interval excluding zero in one run. These results indicate that HIJP’s advantage on Push-T comes mainly from longer-horizon tasks rather than a uniform improvement across levels.
Response to Reviewer oBJe (Part 3)
Q3. Can you compare total planning latency and success against INTACT and several CEM budgets, at batch size one as well as 50, under the same replanning schedule?
A3: Thank you for the suggestion. We compared HIJP, INTACT Direct, and LeWM + CEM with four search budgets on the same start–goal pairs and with the same replanning schedule: all methods replanned every 25 environment steps. LeWM + CEM plans with LeWM’s own encoder and forward model, and its budget is the number of candidate action sequences evaluated per planning call. We report success rates, planning time per call, and total planning time per episode at batch sizes of 1 and 50, averaged across the four environments and four difficulty levels.
Both HIJP and INTACT Direct predict latent states step by step as they generate an action sequence. The original HIJP implementation then performs two additional rollouts of the generated action sequence to compute the initial and final planning costs. In the search-free setting (), neither computation affects action selection. INTACT Direct instead computes its diagnostic metrics from the final latent state predicted during action generation. We therefore report timings for both the original HIJP implementation and a version that skips the two additional rollouts while keeping the original action generation procedure.
| Method | B1 success (%) | B50 success (%) | B1 planning per call (ms) | B50 planning per call, 50 envs (ms) | B1 total planning per episode (s) | B50 total planning per episode (s) |
|---|---|---|---|---|---|---|
| HIJP (original implementation) | 86.6 | 86.9 | 49.3 | 76.4 | 0.140 | 0.004 |
| HIJP (without extra rollouts) | 86.5 | 86.8 | 20.8 | 35.8 | 0.058 | 0.002 |
| INTACT Direct | 81.8 | 81.9 | 25.4 | 46.3 | 0.072 | 0.003 |
| LeWM + CEM (60) | 51.8 | 52.1 | 128.8 | 1,539.9 | 0.373 | 0.086 |
| LeWM + CEM (250) | 62.1 | 62.1 | 271.3 | 6,785.9 | 0.740 | 0.372 |
| LeWM + CEM (1,000) | 65.2 | 66.5 | 1,035.2 | 27,278.3 | 2.838 | 1.494 |
| LeWM + CEM (2,250) | 67.0 | 69.0 | 1,798.3 | 59,784.1 | 4.931 | 3.274 |
With the extra rollouts skipped, HIJP took 20.8 ms per planning call at a batch size of 1, compared with 49.3 ms for the original implementation and 25.4 ms for INTACT Direct. At a batch size of 50, the corresponding times per batch were 35.8, 76.4, and 46.3 ms. Skipping the rollouts does not change the selected actions: the mean success rates (86.5% at a batch size of 1 and 86.8% at 50) were within 0.1 percentage points of the original implementation and remained above those of INTACT Direct (81.8% and 81.9%). The version without the extra rollouts was timed in a separate session from the other rows, so its comparison with INTACT Direct is approximate; the two methods perform a similar amount of computation per call (two encodings, five action predictions, and five forward-model steps). At both batch sizes, HIJP achieved a higher mean success rate and a lower total planning time per episode than LeWM + CEM at every tested search budget.
The original HIJP implementation spent more planning time than INTACT Direct; after skipping the two rollouts used only to log diagnostic costs, the two were comparable (0.058 vs. 0.072 s per episode at a batch size of 1, and 0.002 vs. 0.003 s at 50).
Response to Reviewer oBJe (Part 1)
Thank you for your careful review and constructive comments. We are glad that you recognize how HIJP combines the inverse and forward dynamics models and how the component ablations support the individual design choices. We also appreciate your positive assessment of HIJP’s performance on Push-T and OGCube and its efficiency advantage over the CEM planner we evaluated at the same replanning frequency. To address your questions about evaluation independence, the reliability of the results, and the efficiency comparison, we conducted additional experiments and respond to each point below.
Q1: Are evaluation trajectories or initial/goal observations disjoint from training at the episode level? Please specify the episode-level split and which observations are available during training.
A1: Thank you for pointing out that the original manuscript did not clearly explain the relationship between training trajectories and evaluation episodes. The window-level split described in Appendix A.1 was used for training and validation. After reconstructing the evaluation tasks under the original protocol, we found that some evaluation instances in Table 1 came from offline trajectories that contained training windows.
To assess performance on unseen trajectories, we split the data in each environment 90/10 by complete trajectory and retrained both methods on the same 90% of trajectories, following INTACT’s released training and inference configurations for the baseline. All observations and actions used to train both methods, including future observations used to construct training goals, came from these trajectories. The remaining 10% of trajectories were used exclusively for evaluation, and all evaluation start states and goals were sampled from these held-out trajectories.
For each evaluation seed and difficulty level, both methods were evaluated on the same 50 start–goal pairs. We report the mean and sample standard deviation across the three evaluation seeds.
Under the trajectory-level holdout protocol, HIJP and INTACT achieved average success rates of 86.1% and 68.8%, respectively, with equal weight given to each of the 16 task–difficulty combinations. The difference was 17.3 percentage points. HIJP led INTACT by 51.9 percentage points on Two-Room, 12.4 on Push-T, and 9.3 on OGCube, and trailed INTACT by 4.4 percentage points on Reacher. In the revised manuscript, we will explicitly describe the trajectory overlap in the original evaluation and report the split protocol and results of the holdout experiment.