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.
On Stateful Value Factorization in Multi-Agent Reinforcement Learning
1 Pith paper cite this work. Polarity classification is still indexing.
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.
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Fixing Incomplete Value Function Decomposition for Multi-Agent Reinforcement Learning
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.