Joseph Halpern and Xinming Liu Publish “Bounded Rationality in Las Vegas: Probabilistic Finite Automata PlayMulti-Armed Bandits”

03 Aug 2020

Joseph Halpern, CHAI PI and Professor at Cornell University, and Xinming Liu published their paper at Uncertainty in AI (UAI)’s Virtual Conference which was held August 3rd to 6th.

The following is a summary of the paper:

“While traditional economics assumes that humans are fully rational agents who always maximize their expected utility, in practice, we constantly observe apparently irrational behavior. One explanation is that people have limited computational power, so that they are, quite rationally, making the best decisions they can, given their computational limitations. To test this hypothesis, we consider the multi-armed bandit (MAB) problem. We examine a simple strategy for playing an MAB that can be implemented easily by a probabilistic finite automaton (PFA). Roughly speaking, the PFA sets certain expectations, and plays an arm as long as it meets them. If the PFA has sufficiently many states, it performs near-optimally. Its performance degrades gracefully as the number of states decreases. Moreover, the PFA acts in a ‘human-like’ way, exhibiting a number of standard human biases, like an optimism bias and a negativity bias.”

You can download the paper from this link.