imitation learning

We propose a method for quantifying the similarity of learned reward functions without performing policy learning and evaluation.

Write-up on Super Smash Bros. 64 AI developed using behavioral cloning.

One potential method for validating autonomous vehicles is to evaluate them in a simulator. For this to work, you need highly realistic models of human driving behavior. Existing research learned human driver models using generative adversarial imitation learning, but did so in a single-agent environment. As a result, the model fails when you execute many of the learned policies simultaneously. This research performs training in a multi-agent setting to address this problem.