ISA uses mutual information between actions and state changes to define each agent's influence scope, then uses it for credit assignment and count-based exploration in sparse-reward MARL.
MASER: multi-agent rein- forcement learning with subgoals generated from experi- ence replay buffer
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Credit Assignment and Efficient Exploration based on Influence Scope in Multi-agent Reinforcement Learning
ISA uses mutual information between actions and state changes to define each agent's influence scope, then uses it for credit assignment and count-based exploration in sparse-reward MARL.