User:IssaRice/AI safety/Comparison of terms related to agency

From Machinelearning
Revision as of 22:54, 2 September 2019 by IssaRice (talk | contribs)
Term Opposite
Agent
Optimizer, optimization process
consequentialist
expected utility maximizer
goal-directed, goal-based
pseudoconsequentialist

parameters to check for:

  • is it searching through a list of potential answers?
  • does it have an explicit model of the world?
  • can it be modeled as having a utility function?
  • can we take an intentional stance toward it? i.e., is it useful (so far as predicting what it will do is concerned) to model it as having intentions?

examples to check against:

  • humans
  • evolution/natural selection
  • bottlecap
  • RL system playing Pong without an explicit model