Yup, including better models of human irrationality seems like a promising direction for CIRL. I’ve been writing up a short note on the subject with more explicit examples- if you want to work on this without duplicating effort, let me know and I’ll share the rough draft with you.
Yup, including better models of human irrationality seems like a promising direction for CIRL. I’ve been writing up a short note on the subject with more explicit examples- if you want to work on this without duplicating effort, let me know and I’ll share the rough draft with you.
Ok, send me the draft.