- Rating
- 3
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This work proposed RoboMemArena, a benchmark for long-horizon tasks with partial observability, and PrediMem, a hierarchical policy which selects relevant keyframes to store in its memory. Additionally, PrediMem trains with an auxiliary loss to predict the future latent frames. They evaluate on 26 simulated tasks with subtask labels and 8 real-world tasks on a bimanual platform.
Critical strengths
- The component-wise ablations for PrediMem are comprehensive and help illustrate the benefits of predictive coding heads and the keyframe bank.
- RoboMemArena is one of a few simulated benchmarks that focus on memory for long-horizon tasks. Additionally, the have procedural data generation which allows researchers to generate data for there own long-horizon memory tasks and test the effects of scaling data.
- The organization, writing, and figures are clear.
Critical weaknesses
- The justification for predictive coding being beneficial in section 4 is hard to follow. It's unclear that this auxiliary objective will help the model decide what keyframes to select.
- There are lack of results on established memory benchmarks like RoboMME. This would help show PrediMem's benefits generalize to other settings that require memory.
Questions for authors
- Could you add an experiment showing the keyframe selection precision and recall with and without using the predictive coding auxiliary objective? This can help justify the claim made in section 4 about the benefits of predictive coding. This can help complement the t-SNE visualization in figure 5.
- Could you results from one external memory benchmark like RoboMME for PrediMem and its ablations?
- What backbone was used for the high-level policy of MemER? What were the training hyperparameters used for each method and baseline?