Decision Theory with Resource-Bounded Agents
This work addresses the challenge of incorporating computational limits into decision theory, which is incremental as it reviews and applies existing approaches to explain human biases and optimize performance.
The paper tackles the problem of modeling resource-bounded agents in decision theory by reviewing two approaches: one charging for computation costs to explain biases like first-impression-matters and belief polarization, and another modeling agents as finite automata with an algorithm that provably performs optimally as states increase.
There have been two major lines of research aimed at capturing resource-bounded players in game theory. The first, initiated by Rubinstein, charges an agent for doing costly computation; the second, initiated by Neyman, does not charge for computation, but limits the computation that agents can do, typically by modeling agents as finite automata. We review recent work on applying both approaches in the context of decision theory. For the first approach, we take the objects of choice in a decision problem to be Turing machines, and charge players for the ``complexity'' of the Turing machine chosen (e.g., its running time). This approach can be used to explain well-known phenomena like first-impression-matters biases (i.e., people tend to put more weight on evidence they hear early on) and belief polarization (two people with different prior beliefs, hearing the same evidence, can end up with diametrically opposed conclusions) as the outcomes of quite rational decisions. For the second approach, we model people as finite automata, and provide a simple algorithm that, on a problem that captures a number of settings of interest, provably performs optimally as the number of states in the automaton increases.