Pith. sign in

REVIEW 1 cited by

On Stateful Value Factorization in Multi-Agent Reinforcement Learning

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2408.15381 v2 pith:7II5QU43 submitted 2024-08-27 cs.AI

classification cs.AI
keywords factorizationtheorymethodscurrentfullhistorylearningmulti-agent
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Value factorization is a popular paradigm for designing scalable multi-agent reinforcement learning algorithms. However, current factorization methods make choices without full justification that may limit their performance. For example, the theory in prior work uses stateless (i.e., history) functions, while the practical implementations use state information -- making the motivating theory a mismatch for the implementation. Also, methods have built off of previous approaches, inheriting their architectures without exploring other, potentially better ones. To address these concerns, we formally analyze the theory of using the state instead of the history in current methods -- reconnecting theory and practice. We then introduce DuelMIX, a factorization algorithm that learns distinct per-agent utility estimators to improve performance and achieve full expressiveness. Experiments on StarCraft II micromanagement and Box Pushing tasks demonstrate the benefits of our intuitions.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Fixing Incomplete Value Function Decomposition for Multi-Agent Reinforcement Learning

    cs.LG 2025-05 conditional novelty 6.0 of 10

    QFIX adds a lightweight positive-weight fixing layer to VDN/QMIX, achieving the full individual-global-max function class more simply than QPLEX and with better empirical performance.

Pith tools