Eliezer, do you think that this search for magic and mystery always outside the known world is some side-effect of human reinforcement learning?
As far as I know it could be a loose knob on the tuning device for the exploit/explore tradeoff.
Pick a username and password for your Less Wrong and Less Wrong Wiki accounts. You will receive an email to verify your account.
Create account
Already have an account and just want to login?
Login
Forgot your password?
= 27d567bc2d48d9f40e9ccc20ea370b15)
= b715d02e85f7b3b4ae65ca3d3e450868)
Subscribe to RSS Feed
= f037147d6e6c911a85753b9abdedda8d)
Eliezer, do you think that this search for magic and mystery always outside the known world is some side-effect of human reinforcement learning?
As far as I know it could be a loose knob on the tuning device for the exploit/explore tradeoff.