Bounded Rationality in Las Vegas: Probabilistic Finite Automata PlayMulti-Armed Bandits | AISC
Speaker(s): Xinming Lily Liu
Facilitator(s): Jiri Stodulka
Find the recording, slides, and more info at https://ai.science/e/bounded-rationality-in-las-vegas-probabilistic-finite-automata-play-multi-armed-bandits--5ehKHjM2GVzWAlmNSRg0
Motivation / Abstract
The main motivation for this study was to develop an understanding of human behavior. The researchers examine how reinforcement learning, specifically multi-arm bandit, can mimic a human-like behavior through probabilistic finite automaton (PFA). According to the performed experiments, one can then observe human bias behavior exhibited by the machine.
What was discussed?
- what can be a business application of the method/findings?
- where else we in economics or human decision tasks we can observe such setting?
------
#AISC hosts 3-5 live sessions like this on various AI research, engineering, and product topics every week! Visit https://ai.science for more details