Skip to content

Question about TMC definition and Mem-0 comparison #16

Description

@arlisgreat

Hi authors, thanks for releasing RMBench. I have two questions:

  1. TMC is defined by the minimum number of “task-relevant observations,” but how are “task-relevant” and “encoded from an observation” operationally determined? Since the memory representation is unrestricted, it seems possible to compress an arbitrary history into a fixed-size state, so the number of retained frames may not reflect memory complexity.

  2. On M(n) tasks, Mem-0 also introduces subtask decomposition, a planner, subtask supervision, and a termination classifier, while the baselines do not use decomposition. Does Table 1 therefore measure the gain of the complete hierarchical system rather than memory alone?

Could you clarify these points or provide a comparison where only the memory input is changed?

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions