Reinforcement Learning Journal, vol. TBD, 2025, pp. TBD.
Presented at the Reinforcement Learning Conference (RLC), Edmonton, Alberta, Canada, August 5–9, 2025.
This paper studies two popular objective specification mechanisms for sequential decision-making: goals and rewards. We investigate how easy it is for people without AI expertise to use these different specification mechanisms effectively. Specifically, through this paper, we investigate how effectively these mechanisms could be used to (a) correctly direct an AI system or robot to generate some desired behavior and (b) predict the behavior encoded in a given objective specification. We first present a formalization of the problems of objective specification and behavior prediction, and we characterize the problems of underspecification and overspecification. We then perform a user study to assess how well participants are able to use rewards and goals as specification mechanisms, and their propensity for overspecification and underspecification with these mechanisms. While participants have a strong preference for using goals as an objective specification mechanism, we find a surprising result: even non-expert users are equally capable of specifying and interpreting reward functions as of using goals.
Septia Rani, Serena Booth, and Sarath Sreedharan. "Goals vs. Rewards: A Preliminary Comparative Study of Objective Specification Mechanisms." Reinforcement Learning Journal, vol. TBD, 2025, pp. TBD.
BibTeX:@article{rani2025goals,
title={Goals vs. Rewards: {A} Preliminary Comparative Study of Objective Specification Mechanisms},
author={Rani, Septia and Booth, Serena and Sreedharan, Sarath},
journal={Reinforcement Learning Journal},
year={2025}
}