- Rating
- 1
- Confidence
- 4
- Informativeness
- 1
- Presentation
- 1
- Soundness
- 1
Read review
Paper summary
In this paper, the authors propose Action2Delta, a two LLM framework, where actor agent tries to finish the tasks, and the dynamics agent tries to estimate the consequence of the model. CDD teach the dynamics model to learn what an action changes and VRA train the actor agent based on the training signals provided by the dynamics model. The authors demonstrate the effectiveness of this paper in various tasks.
Critical strengths
- Well motivated object, a dynamic model as the world model is a good starting point.
- Explicit limitation, the authors make a clear discussion on the limitations of this paper.
Critical weaknesses
- The gains on multiple tasks still lack adequate uncertainty estimates.
- Some results need to clarify. In Table 37, all 30 ScienceWorld task scores satisfy exactly In Table 36, improvements are identical across all six ALFWorld task families.
Questions for authors
- Can you provide uncertainty of some of the most important results?
- Are Tables 36 and 37 direct aggregations of evaluated episodes? Please explain their exact numerical relationships and provide the underlying task/seed outcomes and aggregation procedure.