ASALT uses observation-level and state-level adapters to align mismatched dimensionalities into a shared embedding for transferring actors and critics in MARL, showing improved sample efficiency and reduced negative transfer in cooperative benchmarks.
Cooperative multiagent transfer learning with coalition pattern decomposition
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
ASALT: Adaptive State Alignment for Lateral Transfer in Multi-agent Reinforcement Learning
ASALT uses observation-level and state-level adapters to align mismatched dimensionalities into a shared embedding for transferring actors and critics in MARL, showing improved sample efficiency and reduced negative transfer in cooperative benchmarks.