AIR adds an adaptive bonus based on an identity classifier to Q-values, switching between individual and collective exploration by the sign of a learned temperature.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
AIR: Unifying Individual and Collective Exploration in Cooperative Multi-Agent Reinforcement Learning
AIR adds an adaptive bonus based on an identity classifier to Q-values, switching between individual and collective exploration by the sign of a learned temperature.