- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 1
- Soundness
- 2
Read review
Paper summary
This paper builds on the key insight that for compositional world models, state coverage is not enough, actuators needs to be observed in relevant state contexts. Through scientific studies through the problem of single-actuator data, this paper shows that changing actuator–state pairings while holding the state pool and per-actuator action marginals fixed improves prediction of unseen actuator combinations. This is further accompanied with a theoretical argument on linear switch-system class and proposes a data-collection strategy that switches actuators without resetting the state, improving compositional prediction at a matched interaction budget.
Critical strengths
- It studies an interesting problem of how to collect data in a single-actuator regime such that the learned world model can generalize better to unseen state-action combinations.
Critical weaknesses
- Writing is hard to follow. The introduction does not provide clear enough motivation for the project, and the related works does not provide enough context for readers to understand the problem setting.
Questions for authors
- Could the authors provide a targeted matched-pool and reset-versus-carried using additive / action-affine learner for comparison under the final experimental protocal?