System Neural Diversity
Cross-source consensus on System Neural Diversity from 1 sources and 5 claims.
1 sources · 5 claims
How it works
Risks & contraindications
Comparisons
Highlighted claims
- Full SND requires n choose 2 pairwise computations for every metric call. — Graph-SND: Sparse Aggregation for Behavioral Diversity in Multi-Agent Reinforcement Learning
- SND measures behavioral heterogeneity in multi-agent reinforcement learning using average pairwise distances between agents' action distributions. — Graph-SND: Sparse Aggregation for Behavioral Diversity in Multi-Agent Reinforcement Learning
- In Gaussian-policy settings, the pairwise behavioral distance is computed using Monte Carlo averages of Wasserstein-2 distances over rollout observations. — Graph-SND: Sparse Aggregation for Behavioral Diversity in Multi-Agent Reinforcement Learning
- All-pairs SND aggregation can become a bottleneck when evaluated repeatedly during training or control. — Graph-SND: Sparse Aggregation for Behavioral Diversity in Multi-Agent Reinforcement Learning
- All-pairs SND aggregation should be treated as a design choice rather than an unavoidable default. — Graph-SND: Sparse Aggregation for Behavioral Diversity in Multi-Agent Reinforcement Learning