Quantifying the effects of environment and population diversity in multi-agent reinforcement learning

Understand

Generalization is a major challenge for multi-agent reinforcement learning.

• How well does an agent perform when placed in novel environments and in interactions with new co-players? In this paper, we investigate and quantify the relationship between generalization and diversity in the multi-agent domain.
• Across the range of multi-agent environments considered here, procedurally generating training levels significantly improves agent performance on held-out levels.
• However, agent performance on the specific levels used in training sometimes declines as a result.