Combining Reward Information from Multiple Sources

Understand

Given two sources of evidence about a latent variable, one can combine the information from both by multiplying the likelihoods of each piece of evidence.

• However, when one or both of the observation models are misspecified, the distributions will conflict.
• We study this problem in the setting with two conflicting reward functions learned from different sources.
• In such a setting, we would like to retreat to a broader distribution over reward functions, in order to mitigate the effects of misspecification.