- Rating
- 3
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
The paper proposes to generate synthetic "memory" with world model simulations. When the agent makes a mistake, it tries to generate alternative actions based on the experience. The world model examines whether these actions are actually helpful compared with the original one. If so, the new trajectory is logged in the agent's memory for future use. The method is demonstrated effective on multiple benchmarks and backbones.
Critical strengths
- The experiments are extensive and the results are strong.
- The presentation of the paper is easy to follow, and the method is clean and simple.
Critical weaknesses
- The method uses oracle world models, which are not always available in general tasks. This limits the impact of the paper.
Questions for authors
- Does your method work with trained world models?