Graph-SND
Cross-source consensus on Graph-SND from 1 sources and 5 claims.
1 sources · 5 claims
Uses
How it works
Benefits
Comparisons
Highlighted claims
- Graph-SND is defined as a weighted mean of pairwise behavioral distances over graph edges. — Graph-SND: Sparse Aggregation for Behavioral Diversity in Multi-Agent Reinforcement Learning
- Graph-SND exactly recovers SND when the aggregation graph is the complete graph with unit weights. — Graph-SND: Sparse Aggregation for Behavioral Diversity in Multi-Agent Reinforcement Learning
- Graph-SND modifies only the aggregation layer of SND while leaving policies, training, rollout estimation, and pairwise distances unchanged. — Graph-SND: Sparse Aggregation for Behavioral Diversity in Multi-Agent Reinforcement Learning
- Graph-SND evaluation on a precomputed graph reduces pairwise computations from all unordered pairs to only graph edges. — Graph-SND: Sparse Aggregation for Behavioral Diversity in Multi-Agent Reinforcement Learning
- Graph-SND can express complete, local, and sparse random aggregation regimes. — Graph-SND: Sparse Aggregation for Behavioral Diversity in Multi-Agent Reinforcement Learning