Difference between revisions of "Utility extraction"

From Lesswrongwiki
Jump to: navigation, search
 
(2 intermediate revisions by 2 users not shown)
Line 11: Line 11:
 
Thomas D. Nielsen and Finn V. Jensen ([http://people.cs.aau.dk/~tdn/papers/nielsen-jensen-04-ai.pdf Learning a decision maker’s utility function from (possibly) inconsistent behavior]) were the first describing two algorithms that can take into account inconsistent behaviors. Inconsistent choices are interpreted as random deviations from an underlying “true” utility function.  
 
Thomas D. Nielsen and Finn V. Jensen ([http://people.cs.aau.dk/~tdn/papers/nielsen-jensen-04-ai.pdf Learning a decision maker’s utility function from (possibly) inconsistent behavior]) were the first describing two algorithms that can take into account inconsistent behaviors. Inconsistent choices are interpreted as random deviations from an underlying “true” utility function.  
  
Another possibility according to Luke Muehlhauser and Louie Helmis ([http://intelligence.org/files/SaME.pdf The Singularity and Machine Ethics]) is interpreting inconsistent choices as deviations produced by non-model-based valuation systems in the brain; information on when and to what extent model-based choices are “overruled” by the non-model-based valuation systems is provided by neuroscientific research.
+
Another possibility is described in [http://intelligence.org/files/SaME.pdf The Singularity and Machine Ethics] by Luke Muehlhauser and Louie Helm. Research has recently postulated that the neural encoding of human values results from an interaction of two kinds of valuation processes:  “model-free” processes, based on simplified past experience (e.g. habits and reinforcements), and “model-based” processes, associated with deliberative, computationally expensive goal-directed behavior. According to Muehlhauser and Helm inconsistent choices can be interpreted as deviations produced by non-model-based valuation systems; predictions on when and to what extent model-based choices are “overruled” by the non-model-based valuation systems are provided by neuroscientific research.
 
 
Finally, another option is represented by "value learners", implemented agents flexible enough to be used even when a detailed specification of desired behavior is not known. As they can pursue any goal, they can be designed to treat human goals as final rather than instrumental goals ([http://intelligence.org/files/LearningValue.pdf Learning What to Value]). Agents are provided with a pool of possible utility functions and a probability distribution P given a particular interaction history: they can therefore calculate expected value over possible utility functions.
 
  
 
==Further Reading & References==
 
==Further Reading & References==

Latest revision as of 06:57, 13 October 2012

Utility extraction is the semi-automatic acquisition of decision maker's preferences about the different outcomes of a decision problem. Extracting human preferences would be of great importance in order to implement them in a Friendly AI, preventing AI’s goals differing from ours in case of a "hard takeoff". However, human values can be difficult to specify.

Research has focused on three different areas:

  • eliciting the utility function based on a database of already elicited utility functions;
  • iterative refinement of the decision maker’s current utility function using a value of information approach;
  • eliciting the utility function based on a database of observed behavioral patterns.

The last approach implies that preferences are reflected in the behavior, and that the decision maker is behavioral consistent. As real-world behaviors and decisions are often not consistent, methods based on such assumptions can extract only trivial utility functions.

Thomas D. Nielsen and Finn V. Jensen (Learning a decision maker’s utility function from (possibly) inconsistent behavior) were the first describing two algorithms that can take into account inconsistent behaviors. Inconsistent choices are interpreted as random deviations from an underlying “true” utility function.

Another possibility is described in The Singularity and Machine Ethics by Luke Muehlhauser and Louie Helm. Research has recently postulated that the neural encoding of human values results from an interaction of two kinds of valuation processes: “model-free” processes, based on simplified past experience (e.g. habits and reinforcements), and “model-based” processes, associated with deliberative, computationally expensive goal-directed behavior. According to Muehlhauser and Helm inconsistent choices can be interpreted as deviations produced by non-model-based valuation systems; predictions on when and to what extent model-based choices are “overruled” by the non-model-based valuation systems are provided by neuroscientific research.

Further Reading & References

See also