Collaborating with Humans without Human Data. (arXiv:2110.08176v2 [cs.LG] UPDATED)

Collaborating with humans requires rapidly adapting to their individual
strengths, weaknesses, and preferences. Unfortunately, most standard
multi-agent reinforcement learning techniques, such as self-play (SP) or
population play (PP), produce agents that overfit to their training partners
and do not generalize well to humans. Alternatively, researchers can collect
human data, train a human model using behavioral cloning, and then use that
model to train "human-aware" agents ("behavioral cloning play", or BCP). While
such an approach can improve the generalization of agents …

arxiv data human humans